Water-land-air intelligent traffic carrying system

Abstract

The invention relates to the technical field of traffic carrying, and discloses a water-land-air intelligent traffic carrying system. The intelligent cooperative management system formulates an intelligent cooperative carrying scheme of the unmanned vehicle, the unmanned aerial vehicle and the unmanned ship, the unmanned vehicle responds to a first instruction of the intelligent cooperative carrying scheme and drives the cargo docking platform to receive the target cargo and move to a preset first connection position, and the unmanned aerial vehicle responds to a second instruction and drives the target cargo to move to the preset first connection position. And the cargo handover device is started to receive the target cargo and move the target cargo to a preset second connection position, the unmanned ship responds to a third instruction, and the telescopic cargo grabbing mechanism is driven to grab the target cargo and move the target cargo to a preset third connection position, so that seamless cargo transfer among the three transportation tools is achieved. The waiting time and manual intervention of goods in the transportation link are reduced, and the logistics transportation efficiency is greatly improved. The technical problems that in an existing traffic carrying system, multiple times of cargo handover are involved in the cargo transportation process on land, on water and in the air, and a large amount of time and labor cost are consumed are solved.

Description

Technical Field

[0001] The present invention relates to the field of transportation technology, and in particular to an intelligent transportation system for land, water and air. Background Art

[0002] With the development of industries such as autonomous driving, drones, and robots, the use of unmanned equipment such as drones for cargo delivery has become increasingly popular. Taking drones as an example, in the current delivery process using drones, drones perform delivery tasks according to the dispatched routes. The drones arrive at the take-off point to load the cargo, and then fly over the landing point to land and unload the cargo.

[0003] However, in the existing transportation system, land, water and air transportation operate independently. When goods are transferred between different transportation modes, manual loading, unloading and transshipment are required. In multimodal transport scenarios, such as transporting goods from inland cities to ports by road, then to overseas by water, and finally to the destination city by air, the entire process involves multiple handovers of goods, which consumes a lot of time and labor costs. At the same time, different transportation tools lack an effective coordination mechanism, making it difficult to achieve efficient cargo delivery and scheduling, and unable to meet the development needs of modern logistics for rapid, accurate and intelligent development. Summary of the invention

[0004] The present invention provides an intelligent land, water and air transportation system, which solves the technical problems in the existing transportation system, that is, the process of transporting goods by land, water and air involves multiple cargo handovers, which consumes a lot of time and manpower costs, and different means of transportation lack an effective coordination mechanism, making it difficult to achieve efficient cargo delivery and scheduling, and unable to meet the technical problems of the rapid, accurate and intelligent development needs of modern logistics.

[0005] The present invention provides a water, land and air intelligent transportation system, which includes an intelligent collaborative management system and a land transportation unmanned vehicle, an air transportation unmanned aerial vehicle and a water transportation unmanned boat, which are respectively connected to the intelligent collaborative management system for communication;

[0006] The intelligent collaborative management system is used to formulate and output an intelligent collaborative transportation plan based on the starting and ending locations, physical data, traffic data and environmental data of the target goods;

[0007] The land transport unmanned vehicle is used to drive the cargo docking platform to receive the target cargo and move to a preset first docking position in response to the received first instruction of the intelligent collaborative transport solution;

[0008] The unmanned water transport boat is used to respond to the received second instruction of the intelligent collaborative transport solution, start the cargo transfer device to receive the target cargo and move to a preset second docking position;

[0009] The aerial transport UAV is used to drive the retractable cargo grabbing mechanism to grab the target cargo and move it to a preset third connection position in response to the third instruction of the received intelligent collaborative transport plan.

[0010] Optionally, the intelligent collaborative management system includes a data analysis module, an intelligent collaborative planning module, and an energy management system;

[0011] The data analysis module is used to obtain the water-land-air collaborative transport information and preprocess the water-land-air collaborative transport information; wherein, the water-land-air collaborative transport information includes the start and end positions, physical data, environmental data, meteorological data, and traffic data of the target cargo;

[0012] The intelligent collaborative planning module is used to formulate an intelligent collaborative transport plan according to the preprocessed start and end positions, physical data, environmental data, meteorological data, and traffic data;

[0013] The energy management system is used to monitor and switch energy supply devices.

[0014] Optionally, the intelligent collaborative planning module is specifically used for:

[0015] According to the preprocessed start and end positions, draw multiple initial water-land-air transport cargo routes for the collaborative transport of the land transport unmanned vehicle, the aerial transport UAV, and the water transport unmanned boat;

[0016] According to the preprocessed environmental data, meteorological data, and traffic data, screen each of the initial water-land-air transport cargo routes to generate multiple updated water-land-air transport cargo routes and form a water-land-air transport cargo route set;

[0017] Based on the genetic algorithm, set the water-land-air transport cargo route set as the initial particle swarm and calculate the fitness function of each updated water-land-air transport cargo route in the initial particle swarm; wherein, the calculation formula of the fitness function is:

[0018]

[0019] In the formula, Length represents the length of the water-land-air transport cargo path, WeatherFactor represents the influence factor calculated according to the weather data, TrafficFactor represents the congestion factor calculated according to the traffic data, ChangeCost represents the equipment replacement cost for the equipment replacement of the land transport unmanned vehicle, the aerial transport UAV, and the water transport unmanned boat, and w1, w2, w3, and w4 all represent weight coefficients;

[0020] Select the updated water, land, and air cargo transportation routes according to the fitness function values corresponding to the fitness functions of the initialized particle swarm to generate a genetic particle swarm.

[0021] Perform crossover operations and mutation operations on each updated water, land, and air cargo transportation route of the genetic particle swarm in sequence to generate an updated genetic particle swarm.

[0022] Determine whether the current iteration number of the updated genetic particle swarm is greater than or equal to the first preset iteration number threshold.

[0023] If not, set the current updated genetic particle swarm as the new initialized particle swarm, and jump to execute the step of calculating the fitness functions of the updated water, land, and air cargo transportation routes of the initialized particle swarm. Repeat this process until the current iteration number of the current updated genetic particle swarm is greater than or equal to the first preset iteration number threshold, then obtain the optimal water, land, and air cargo transportation route.

[0024] Optionally, the intelligent collaborative planning module is further specifically configured to:

[0025] Determine the vehicle type of the land transport unmanned vehicle, the aircraft type of the air transport unmanned aerial vehicle, and the boat type of the water transport unmanned boat according to the preprocessed physical data.

[0026] Based on the optimal water, land, and air cargo transportation route, determine the preset first connection position of the land transport unmanned vehicle, the preset second connection position of the air transport unmanned aerial vehicle, and the preset third connection position of the boat type of the water transport unmanned boat.

[0027] Formulate an intelligent collaborative transportation plan by using the optimal water, land, and air cargo transportation route, the vehicle type of the land transport unmanned vehicle, the aircraft type of the air transport unmanned aerial vehicle, the boat type of the water transport unmanned boat, the preset first connection position, the preset second connection position, and the preset third connection position.

[0028] Analyze the water, land, and air collaborative transportation data in the intelligent collaborative transportation plan, and generate a first instruction, a second instruction, and a third instruction according to the analysis result.

[0029] Optionally, an electronic tag is set on the target cargo for identifying the current position of the target cargo.

[0030] Optionally, the land transport unmanned vehicle includes a land transport unmanned vehicle body.

[0031] An automatic driving system, a first tag recognition device, and an energy supply device are provided inside the land transport unmanned vehicle body, and a cargo docking platform is arranged on the top of the land transport unmanned vehicle body.

[0032] The automatic driving system is used to automatically drive the vehicle to the preset first connection position.

[0033] The first tag recognition device is used to recognize the electronic tag on the target goods;

[0034] The goods docking platform is a robotic arm and / or an automatic transportation device, and is used to transfer the target goods with the aerial carrier drone or the waterborne carrier unmanned boat;

[0035] The energy supply device includes a rechargeable battery, a hydrogen fuel cell, and a fuel engine, and is used to execute the operation of switching the energy supply device in response to the received energy switching instruction of the energy management system, and supply power to the autonomous driving system, the goods docking platform, and the first tag recognition device.

[0036] Optionally, the intelligent collaborative planning module is further specifically used for:

[0037] Using the physical data of the target goods, the physical information of the robotic arm, and the environmental data, construct multiple robotic arm cargo handling planning schemes, and form a robotic arm cargo handling planning set;

[0038] Taking the shortest handling time, the shortest handling path length, and the least energy consumption of the robotic arm as the target conditions, construct an objective function;

[0039] According to the physical data of the robotic arm and the environmental data, construct constraint conditions;

[0040] Using the objective function and the constraint conditions, construct a cargo handling model;

[0041] Based on the grey wolf algorithm, set the robotic arm cargo handling planning set as the initial wolf pack;

[0042] Input the initial wolf pack into the cargo handling model, and output the fitness values of each grey wolf in the initial wolf pack;

[0043] According to the fitness values of each grey wolf, determine the alpha wolf, beta wolf, and delta wolf, and based on the fitness value of the alpha wolf, adjust the positions of each grey wolf to generate an updated wolf pack;

[0044] Count the current iteration number, and determine whether the current iteration number is greater than or equal to the second preset iteration number threshold;

[0045] If not, then use the updated wolf pack as the new initial wolf pack, jump to execute the step of inputting the initial wolf pack into the cargo handling model and outputting the fitness values of each grey wolf in the initial wolf pack, until the current iteration number is equal to the second preset iteration number threshold, and determine the optimal solution to obtain the optimal robotic arm cargo handling plan;

[0046] Generate a fourth instruction according to the control instruction corresponding to the optimal robotic arm cargo handling solution;

[0047] Control the robotic arm to perform the operation of handling the target cargo according to the fourth instruction.

[0048] Optionally, the unmanned surface vehicle includes an unmanned surface vehicle body;

[0049] An environment-friendly power system, an intelligent cargo storage and fixing device, and a second tag identification device are built in the unmanned surface vehicle body, and a cargo transfer device is also arranged on the unmanned surface vehicle body;

[0050] The environment-friendly power system is used to drive the unmanned surface vehicle body to a preset second connection position;

[0051] The intelligent cargo storage and fixing device is used to store and fix the target cargo;

[0052] The second tag identification device is used to identify the electronic tag on the target cargo;

[0053] The cargo transfer device is used to transfer the target cargo with the unmanned ground vehicle or the unmanned aerial vehicle.

[0054] Optionally, the unmanned aerial vehicle includes an unmanned aerial vehicle body;

[0055] An automatic flight system, a third tag identification device, and a rechargeable battery and / or fuel power system are arranged in the unmanned aerial vehicle body. A high-precision positioning system and an intelligent obstacle avoidance device are arranged in the automatic flight system, and a telescopic cargo grabbing mechanism is arranged at the bottom of the unmanned aerial vehicle body;

[0056] The automatic flight system is used to drive the unmanned aerial vehicle to a preset third connection position;

[0057] The third tag identification device is used to identify the electronic tag on the target cargo;

[0058] The telescopic cargo grabbing mechanism is used to grab the target cargo and transfer the target cargo with the unmanned ground vehicle or the unmanned surface vehicle;

[0059] The rechargeable battery and / or fuel power system is used to supply power to the automatic flight system, the high-precision positioning system, the intelligent obstacle avoidance device, the third tag identification device, and the telescopic cargo grabbing mechanism.

[0060] Optionally, the intelligent obstacle avoidance device is specifically used for:

[0061] Obtain the first measured distance data of the lidar in the aerial transport UAV, the estimated distance data obtained from image processing of the camera, and the second measured distance data of the millimeter-wave radar;

[0062] Based on the Kalman filtering algorithm, perform data fusion processing on the first measured distance data, the estimated distance data obtained from image processing, and the second measured distance data;

[0063] Calculate the obstacle distance estimation values of the first measured distance data, the estimated distance data obtained from image processing, and the second measured distance data after data fusion processing; wherein, the calculation formula for the obstacle distance estimation value is:

[0064]

[0065] In the formula, d lidar represents the first measured distance data, d cam represents the estimated distance data obtained from image processing, d radar represents the second measured distance data; respectively represent the measurement noise variances of the first measured distance data, the estimated distance data obtained from image processing, and the second measured distance data;

[0066] Control the aerial transport UAV to perform obstacle avoidance processing according to the obstacle distance estimation value.

[0067] As can be seen from the above technical solutions, the present invention has the following advantages:

[0068] The present invention formulates an intelligent collaborative transportation plan for three transportation tools, namely, a land transport unmanned vehicle, an aerial transport UAV, and a water transport unmanned boat, through an intelligent collaborative management system. The land transport unmanned vehicle responds to the instructions of the intelligent collaborative transportation plan, drives the cargo docking platform to receive the target cargo and move to a preset first connection position. The aerial transport UAV responds to the instructions of the intelligent collaborative transportation plan, activates the cargo transfer device to receive the target cargo and move to a preset second connection position. The water transport unmanned boat responds to the instructions of the intelligent collaborative transportation plan, drives the retractable cargo grabbing mechanism to grab the target cargo and move to a preset third connection position, so as to achieve seamless cargo transfer between the unmanned vehicle, the UAV, and the unmanned boat, reduce the waiting time and manual intervention in the transportation link, and greatly improve the logistics transportation efficiency. Moreover, the unmanned vehicle, the UAV, and the unmanned boat all transport the cargo according to the intelligent collaborative transportation plan to ensure the optimal planning and accurate delivery of the cargo transportation path, and reduce the risk of cargo loss and damage. The three transportation tools, namely, the unmanned vehicle, the UAV, and the unmanned boat, realize collaborative operations under the unified command of the intelligent collaborative management system, improve the intelligent level of the entire traffic logistics system and the ability to handle complex situations. Description of the Drawings

[0069] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0070] Figure 1 It is a schematic structural diagram of a land, water and air intelligent transportation and carrying system provided in Embodiment 1 of the present invention;

[0071] Figure 2 It is a schematic structural diagram of another land, water and air intelligent transportation and carrying system provided in Embodiment 2 of the present invention;

[0072] Figure 3 It is a schematic diagram of the exchange process of goods among three kinds of carrying tools of land, water and air provided in Embodiment 2 of the present invention. Detailed implementation manners

[0073] The embodiments of the present invention provide a land, water and air intelligent transportation and carrying system, which is used to solve the technical problems in the existing transportation and carrying system that the process of transporting goods on land, water and air involves multiple goods handovers, consuming a large amount of time and labor costs, and there is a lack of an effective coordination mechanism among different transportation tools, making it difficult to achieve efficient goods transfer and scheduling, and unable to meet the development needs of modern logistics for speed, accuracy and intelligence.

[0074] In order to make the invention purpose, features and advantages of the present invention more obvious and understandable, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the embodiments described below are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0075] Please refer to Figure 1 , Figure 1 It is a schematic structural diagram of a land, water and air intelligent transportation and carrying system provided in Embodiment 1 of the present invention.

[0076] A land, water and air intelligent transportation and carrying system provided by the present invention, the land, water and air intelligent transportation and carrying system includes an intelligent collaborative management system, and a land carrying unmanned vehicle, an air carrying unmanned aerial vehicle and a water carrying unmanned boat respectively communicatively connected to the intelligent collaborative management system.

[0077] In an embodiment of the present invention, the intelligent collaborative management system refers to an intelligent dispatching center, which is specifically the core of the entire system. According to factors such as cargo transportation demand, traffic conditions, weather conditions, etc., it intelligently plans cargo delivery routes and transportation plans to achieve collaborative operation of three types of transportation tools. Through big data analysis and artificial intelligence algorithms, it collects and processes in real time the location, cargo status, operating status and other information of land-based unmanned vehicles, air-based drones and water-based unmanned boats (referred to as unmanned vehicles, drones and unmanned boats), and adjusts the cargo routes and transportation plans of the unmanned vehicles, drones and unmanned boats in real time.

[0078] Land-based unmanned vehicles, air-based drones and water-based unmanned boats all use high-strength, lightweight composite materials to manufacture the bodies of unmanned vehicles, drones and boats. Advanced machining processes are used to ensure the accuracy and reliability of each component. During the production process, strict quality inspections are carried out to ensure that the products meet safety standards.

[0079] Land-based unmanned vehicles, air-based drones, water-based unmanned boats and the intelligent collaborative management system exchange data through a high-speed, stable communication network, transmitting real-time location information, cargo status, task execution status, etc. At the same time, the three types of vehicles also have short-distance communication functions to facilitate real-time coordination and cooperation during cargo delivery.

[0080] The intelligent collaborative management system is used to formulate and output intelligent collaborative transportation plans based on the starting and ending locations, physical data, traffic data and environmental data of the target goods.

[0081] In an embodiment of the present invention, the starting and ending positions of the target cargo are obtained in order to plan the transportation paths of the three types of transport vehicles, namely, unmanned vehicles, unmanned boats and unmanned aerial vehicles. According to the physical data of the target cargo, the type of the unmanned vehicle, the type of the unmanned boat and the type of the unmanned aerial vehicle are determined, as well as the delivery method for seamless cargo delivery between the unmanned vehicles, unmanned aerial vehicles and unmanned boats. Specifically, traffic data and environmental data need to be obtained to facilitate the optimization of the transportation path. The intelligent collaborative management system formulates an intelligent collaborative transportation plan according to the above information, and generates a first instruction, a second instruction and a third instruction according to the intelligent collaborative transportation plan.

[0082] The land transport unmanned vehicle is used to respond to the first instruction of the received intelligent collaborative transport solution, drive the cargo docking platform to receive the target cargo and move it to a preset first docking position.

[0083] In an embodiment of the present invention, when the land-based unmanned vehicle receives the first instruction corresponding to the intelligent collaborative transportation plan, it responds to the first instruction, drives the land-based unmanned vehicle to the starting position of the preset first connection position, and drives the cargo docking platform to receive the target cargo. After securing the target cargo, it transports the target cargo to the end position of the preset first connection position and hands over the target cargo to the water-based unmanned boat or the aerial unmanned drone or reaches the destination.

[0084] Specifically, the cargo docking platform is installed on the land-based unmanned vehicle for cargo handover with the water-based unmanned boat or the aerial unmanned drone.

[0085] The water-based unmanned boat is used to respond to the second instruction of the intelligent collaborative transportation plan, activate the cargo handover device to receive the target cargo and move to the preset second connection position.

[0086] In an embodiment of the present invention, when the water-based unmanned boat receives the second instruction corresponding to the intelligent collaborative transportation plan, it responds to the second instruction, drives the water-based unmanned boat to the starting position of the preset second connection position (this position is the end position of the connection position of the land-based unmanned vehicle or the aerial unmanned drone), and drives the cargo handover device to receive the target cargo. After securing the target cargo, it transports the target cargo to the end position of the preset second connection position and hands over the target cargo to the land-based unmanned vehicle or the aerial unmanned drone or reaches the destination.

[0087] It is worth mentioning that the cargo handover device is installed on the water-based unmanned boat for cargo handover with the land-based unmanned vehicle or the aerial unmanned drone.

[0088] The aerial unmanned drone is used to respond to the third instruction of the intelligent collaborative transportation plan, drive the retractable cargo grabbing mechanism to grab the target cargo and move to the preset third connection position.

[0089] In an embodiment of the present invention, when the aerial unmanned drone receives the third instruction corresponding to the intelligent collaborative transportation plan, it responds to the third instruction, drives the aerial unmanned drone to the starting position of the preset third connection position (this position is the end position of the connection position of the land-based unmanned vehicle or the water-based unmanned boat), and drives the retractable cargo grabbing mechanism to grab the target cargo, and transports the target cargo to the end position of the preset third connection position and hands over the target cargo to the land-based unmanned vehicle or the water-based unmanned boat or reaches the destination.

[0090] It is worth mentioning that the retractable cargo grasping mechanism is installed at the bottom of the aerial transport drone and can extend downward within a preset distance range so that the retractable cargo grasping mechanism can grasp the target cargo. After grasping the target cargo, the target cargo is fixed and contracted upward to avoid the retractable rope for grasping the target cargo being too long during transportation and colliding with obstacles.

[0091] In the embodiment of the present invention, when cargo transfer is required, the intelligent collaborative management system guides the unmanned vehicle, unmanned aerial vehicle, and unmanned boat to the designated handover locations (such as the starting positions of the preset first transfer position, preset second transfer position, and preset third transfer position) according to the pre-planned intelligent collaborative transportation plan. The handover between the unmanned aerial vehicle and the unmanned vehicle or unmanned boat is achieved through precise positioning and grasping devices. For example, when the unmanned aerial vehicle approaches the target transport vehicle, it adjusts its attitude, uses the retractable cargo grasping mechanism to accurately grasp the cargo, and then transports the cargo to the next destination according to the planned route.

[0092] Please refer to Figure 2 , Figure 2 which is a schematic structural diagram of a water-land-air intelligent transportation system provided in the second embodiment of the present invention.

[0093] Figure 3 which is a schematic diagram of the exchange process of goods among three types of transport vehicles, namely water, land, and air, provided in the second embodiment of the present invention.

[0094] For a water-land-air intelligent transportation system provided by the present invention, the intelligent collaborative management system includes a data analysis module, an intelligent collaborative planning module, and an energy management system.

[0095] It should be noted that the data analysis module refers to obtaining various types of perception data from various sensors, cameras, radars, etc., and performing data analysis and data preprocessing on the various types of perception data. The intelligent collaborative planning module refers to organizing the preprocessed various types of perception data and formulating an intelligent collaborative transportation plan according to the cargo transportation requirements. The energy management system refers to a management system that monitors and optimizes the energy supply devices on the unmanned vehicle, unmanned boat, and unmanned aerial vehicle, and switches the energy supply devices under different operating modes.

[0096] In the embodiment of the present invention, the data analysis module performs data analysis and data preprocessing on various types of perception data and transmits them to the intelligent collaborative planning module. The intelligent collaborative planning module intelligently plans the cargo transfer paths and transportation plans of the three types of transport vehicles according to factors such as cargo transportation requirements, traffic conditions, and weather conditions, that is, an intelligent collaborative transportation plan is obtained.

[0097] A data analysis module for obtaining water, land, and air collaborative transportation information and preprocessing the water, land, and air collaborative transportation information; wherein, the water, land, and air collaborative transportation information includes the starting and ending positions, physical data, environmental data, meteorological data, and traffic data of the target cargo.

[0098] It should be noted that the water, land, and air collaborative transportation information refers to various information of devices such as target cargo, unmanned vehicles, unmanned aerial vehicles, and unmanned boats. For example: physical data (dimensions, weight, type) of the target cargo, starting and ending positions required for transportation, environmental data, meteorological data, traffic data, real-time positions of unmanned vehicles, unmanned aerial vehicles, and unmanned boats, loading status, operating conditions, etc.

[0099] In an embodiment of the present invention, by obtaining water, land, and air collaborative transportation information, such as physical data (dimensions, weight, type) of the target cargo, starting and ending positions required for transportation, environmental data, meteorological data, traffic data, real-time positions of unmanned vehicles, unmanned aerial vehicles, and unmanned boats, loading status, operating conditions, etc., and performing data preprocessing on the above information to ensure the security and reliability of the data.

[0100] Among them, the data preprocessing includes the following steps:

[0101] S1. Use the interpolation method to process the missing values in the water, land, and air collaborative transportation information;

[0102] S2. Perform standardization processing on the water, land, and air collaborative transportation information after missing value processing;

[0103] S3. Align the time of the water, land, and air collaborative transportation information after standardization processing;

[0104] S4. Perform symmetric encryption on the water, land, and air collaborative transportation information after time alignment and transmit it to the intelligent collaborative planning module.

[0105] It is worth mentioning that by linearly / spline interpolating to fill in the missing values caused by sensor transmission leakage, communication packet loss, etc., ensuring the continuity of the time series and achieving data integrity, by Z-score standardization to eliminate the dimensional differences of various information, using the dynamic time warping algorithm to unify the time sources of different types of data acquisition devices, solving the planning deviation caused by asynchronous data, and using the symmetric encryption algorithm to encrypt the data before transmission to prevent leakage during the transmission process. The intelligent collaborative planning module decrypts the encrypted water, land, and air collaborative transportation information to ensure the security and reliability of the data.

[0106] An intelligent collaborative planning module for formulating an intelligent collaborative transportation plan according to the preprocessed starting and ending positions, physical data, environmental data, meteorological data, and traffic data.

[0107] In an embodiment of the present invention, the intelligent collaborative planning module intelligently plans the cargo transfer routes and transportation plans of three types of carrier vehicles according to factors such as cargo transportation requirements, traffic conditions, and weather conditions, thereby obtaining an intelligent collaborative transportation plan. During the process of the unmanned vehicle, unmanned aerial vehicle, and unmanned boat carrying cargo, the real-time positions, loading states, operating conditions, etc. of the three types of carrier vehicles are obtained in real time to adjust the intelligent collaborative transportation plan.

[0108] An energy management system for monitoring and switching energy supply devices.

[0109] In an embodiment of the present invention, energy supply devices such as rechargeable batteries, hydrogen fuel cells, and fuel engines are installed on the unmanned vehicle, unmanned boat, and unmanned aerial vehicle and connected to the energy management system. An energy switching test is performed to ensure a smooth transition of energy supply in different operating modes, and at the same time, the energy consumption of the energy supply devices is monitored and optimized. Specifically, in different operating modes, according to the energy consumption situation and environmental requirements, the energy supply method is intelligently switched to achieve efficient utilization of energy and energy conservation and emission reduction.

[0110] It is worth mentioning that the adoption of a diversified energy management system can improve energy utilization efficiency and reduce environmental pollution, which is in line with the concept of sustainable development.

[0111] Optionally, the intelligent collaborative planning module is specifically configured to: draw multiple initial land-air-water cargo transportation routes for the collaborative transportation of the unmanned vehicle for land transportation, unmanned aerial vehicle for air transportation, and unmanned boat for water transportation according to the preprocessed starting and ending positions; screen each initial land-air-water cargo transportation route according to the preprocessed environmental data, meteorological data, and traffic data to generate multiple updated land-air-water cargo transportation routes and form a land-air-water cargo transportation route set; based on the genetic algorithm, set the land-air-water cargo transportation route set as the initial particle swarm and calculate the fitness function of each updated land-air-water cargo transportation route in the initial particle swarm; wherein, the calculation formula of the fitness function is:

[0112]

[0113] Wherein, Length represents the length of the land, water, and air cargo transportation routes, WeatherFactor represents the influence factor calculated based on weather data, TrafficFactor represents the congestion factor calculated based on traffic data, ChangeCost represents the equipment replacement cost for replacing the equipment of the unmanned vehicle for land transportation, the unmanned aerial vehicle for air transportation, and the unmanned boat for water transportation, and w1, w2, w3, and w4 all represent weight coefficients; select operations are performed on each updated land, water, and air cargo transportation route according to the fitness function values corresponding to the fitness functions of the initialized particle swarm to generate a genetic particle swarm; crossover operations and mutation operations are sequentially performed on each updated land, water, and air cargo transportation route of the genetic particle swarm to generate an updated genetic particle swarm; determine whether the current iteration number of the updated genetic particle swarm is greater than or equal to the first preset iteration number threshold; if not, set the current updated genetic particle swarm as the new initialized particle swarm, and jump to execute the step of calculating the fitness function of each updated land, water, and air cargo transportation route of the initialized particle swarm until the current iteration number of the current updated genetic particle swarm is greater than or equal to the first preset iteration number threshold, then the optimal land, water, and air cargo transportation route is obtained.

[0114] It should be noted that the initial land, water, and air cargo transportation routes refer to the land, water, and air cargo transportation routes of the three transportation tools initially planned by the intelligent collaborative planning module through the starting and ending positions of the target cargo.

[0115] The updated land, water, and air cargo transportation routes refer to the remaining land, water, and air cargo transportation routes after the intelligent collaborative planning module screens the feasibility of each initial land, water, and air cargo transportation route based on factors such as cargo transportation requirements, traffic conditions, and weather conditions on the basis of the starting and ending positions of the target cargo.

[0116] The set of land, water, and air cargo transportation routes refers to the set of all updated land, water, and air cargo transportation routes.

[0117] The first preset iteration number threshold can be set according to the actual situation and is not limited here.

[0118] The optimal land, water, and air cargo transportation route refers to the optimal solution obtained by solving each land, water, and air cargo transportation route through the genetic algorithm.

[0119] In the embodiment of the present invention, the intelligent collaborative planning module initially draws multiple initial land, water, and air cargo transportation routes for the collaborative transportation of the unmanned vehicle for land transportation, the unmanned aerial vehicle for air transportation, and the unmanned boat for water transportation according to the preprocessed starting and ending positions; and screens the feasibility of all initial land, water, and air cargo transportation routes according to the preprocessed environmental data, meteorological data, and traffic data, and obtains multiple updated land, water, and air cargo transportation routes after screening. The set of all updated land, water, and air cargo transportation routes is obtained by aggregating them, that is, the set of land, water, and air cargo transportation routes.

[0120] The path planning process according to the genetic algorithm is as follows: Step S1: Represent all updated water, land, and air cargo transportation routes in the form of chromosomes for encoding. For example, integer encoding can be used, and each gene represents a node or a path segment in the water, land, and air cargo transportation routes. For the path planning of unmanned vehicles, unmanned aerial vehicles, and unmanned boats, the chromosome may need to contain device type information and corresponding path information.

[0121] Step S2: Randomly generate a set of initial chromosomes to form an initial population (i.e., the water, land, and air cargo transportation route set). Specifically, the population size is usually determined according to the complexity of the problem and computing resources.

[0122] Step S3: Define a fitness function based on factors such as environmental data, weather data, and traffic data to evaluate the quality of each chromosome. The value of the fitness function represents the quality of the path under given conditions and is usually related to factors such as path length, travel time, and safety. Among them, assuming that the total cost of the path consists of path length, weather impact factor, traffic congestion factor, and equipment replacement cost, the fitness function can be expressed as:

[0123]

[0124] In the formula, Length represents the length of the water, land, and air cargo transportation path, WeatherFactor represents the impact factor calculated based on weather data, TrafficFactor represents the congestion factor calculated based on traffic data, ChangeCost represents the equipment replacement cost for replacing the unmanned vehicle on land, the unmanned aerial vehicle in the air, and the unmanned boat on water, and w1, w2, w3, and w4 all represent weight coefficients.

[0125] It is worth mentioning that 1) Calculation of the weather impact factor: Calculate according to the impact of different weather conditions on the driving speed of the device. For example, for an unmanned aerial vehicle, the speed will decrease in strong wind weather. Assuming the speed of the unmanned aerial vehicle in normal weather is v0 and the speed decreases to v1 in strong wind weather, the weather impact factor can be expressed as:

[0126]

[0127] For unmanned vehicles and unmanned boats, the weather impact factor can be calculated based on a similar principle, combined with the impact of different weather on their driving performance.

[0128] 2) Calculation of the traffic congestion factor: Calculate based on information such as traffic flow and navigation density in traffic data. For example, for an unmanned vehicle, the driving speed will decrease on a road section with heavy traffic. Assuming the speed of the unmanned vehicle on a smooth road section is u0 and the speed on a congested road section is u1, the traffic congestion factor can be expressed as

[0129]

[0130] For an unmanned boat, the traffic congestion factor can be calculated according to factors such as the navigation density of the water area.

[0131] 3) Path length calculation: Calculate the actual length of the path according to the map data and the node coordinates in the path. If the path consists of a series of nodes (x i , y i ), where i = 1, 2,..., n, the path length can be calculated using the Euclidean distance formula or other suitable distance metrics:

[0132]

[0133] 4) Equipment replacement cost calculation: As before, the calculation formula for the equipment replacement cost is:

[0134]

[0135] In the formula, C A , C B are the basic costs of the equipment before and after replacement respectively, is the additional cost at replacement point i, and k t is the time cost coefficient corresponding to time t.

[0136] Step S4: According to the value of the fitness function, select some chromosomes from the current population as parents for generating the next generation. The selection method can be roulette wheel selection, tournament selection, etc.

[0137] Step S5: Perform crossover operations on the selected parent chromosomes to generate new offspring chromosomes. The crossover method can be single-point crossover, multi-point crossover, or uniform crossover, etc., to generate new path combinations by exchanging some genes of the parent chromosomes.

[0138] Step S6: Mutate the chromosomes with a certain probability, randomly change some genes in the chromosomes to increase the diversity of the population and avoid the algorithm falling into a local optimal solution.

[0139] Step S7: Check whether the termination condition is met, such as reaching the maximum number of iterations, the fitness function value converging to a certain degree, etc. If the termination condition is met, stop the algorithm and output the optimal path; otherwise, return to Step S4 to continue the iteration.

[0140] The optimal solution obtained by solving the path planning through the genetic algorithm is the optimal water-land-air cargo transportation route.

[0141] Optionally, the intelligent collaborative planning module is further specifically configured to: determine the vehicle type of the land-based unmanned vehicle, the aircraft type of the aerial unmanned aircraft, and the boat type of the waterborne unmanned boat according to the preprocessed physical data; determine the preset first connection position of the land-based unmanned vehicle, the preset second connection position of the aerial unmanned aircraft, and the preset third connection position of the waterborne unmanned boat based on the optimal land-water-air cargo transportation route; formulate an intelligent collaborative transportation plan by using the optimal land-water-air cargo transportation route, the vehicle type of the land-based unmanned vehicle, the aircraft type of the aerial unmanned aircraft, the boat type of the waterborne unmanned boat, the preset first connection position, the preset second connection position, and the preset third connection position; analyze the land-water-air collaborative transportation data in the intelligent collaborative transportation plan, and generate a first instruction, a second instruction, and a third instruction according to the analysis result.

[0142] In an embodiment of the present invention, the intelligent collaborative planning module analyzes the physical data (size, weight, and type) of the target cargo, so as to know the vehicle type of the land-based unmanned vehicle, the aircraft type of the aerial unmanned aircraft, and the boat type of the waterborne unmanned boat that can transport this target cargo. Obtain the connection positions (i.e., the preset first connection position) where the land-based unmanned vehicle receives and transports the target cargo, the connection positions (i.e., the preset second connection position) where the aerial unmanned aircraft receives and transports the target cargo, and the connection positions (i.e., the preset third connection position) where the waterborne unmanned boat receives and transports the target cargo from the optimal land-water-air cargo transportation route. Formulate an intelligent collaborative transportation plan by using information such as the optimal land-water-air cargo transportation route, the vehicle type of the land-based unmanned vehicle, the aircraft type of the aerial unmanned aircraft, the boat type of the waterborne unmanned boat, the preset first connection position, the preset second connection position, and the preset third connection position. Generate a first instruction, a second instruction, and a third instruction according to the transportation data of the intelligent collaborative transportation plan. Among them, the first instruction is sent to the land-based unmanned vehicle, the second instruction is sent to the waterborne unmanned boat, and the third instruction is sent to the aerial unmanned aircraft. The land-based unmanned vehicle, the waterborne unmanned boat, and the aerial unmanned aircraft respectively respond to the instructions and perform corresponding operations.

[0143] It is worth mentioning that when the real-time positions, loading states, operating conditions, etc. of the three transportation tools are obtained in real time and the intelligent collaborative transportation plan is adjusted, the corresponding modified instruction information is generated, and at the same time, the modified instructions are transmitted to the land-based unmanned vehicle, the waterborne unmanned boat, and the aerial unmanned aircraft, so as to facilitate the timely execution of corresponding operations. Specifically, select stable and reliable communication technologies and equipment, and conduct network architecture design and optimization to ensure high-speed and stable data transmission. For example, 5G / satellite communication ensures data interaction.

[0144] Optionally, an electronic tag is provided on the target cargo for identifying the current position of the target cargo.

[0145] In an embodiment of the present invention, an electronic tag is installed on a target cargo, and real-time positioning of the target cargo and identification of its current position are achieved through radio frequency identification (RFID) technology or other high-precision positioning tags.

[0146] As a preferred embodiment, a Bluetooth / UWB tag can be embedded in the RFID electronic tag. The Bluetooth / UWB tag is used for high-precision positioning at close range, and the RFID electronic tag is used for batch identification at long range. By combining the batch identification ability of RFID and the high-precision positioning technology of Bluetooth / UWB, the combination of batch identification at long range and precise positioning at close range is realized.

[0147] Optionally, the land-based unmanned carrier vehicle includes a land-based unmanned carrier vehicle body; an automatic driving system, a first tag identification device, and an energy supply device are provided inside the land-based unmanned carrier vehicle body, and a cargo docking platform is arranged on the top of the land-based unmanned carrier vehicle body.

[0148] In an embodiment of the present invention, the land-based unmanned carrier vehicle adopts a modular body design, has a flexible cargo space, and can be adjusted according to the size and weight of the target cargo. An advanced automatic driving system is equipped on the land-based unmanned carrier vehicle, which can drive safely under various road conditions. A tag identification device corresponding to the electronic tag of the target cargo is equipped on the unmanned vehicle to facilitate accurate reading of cargo information. An energy supply device such as a rechargeable battery, a hydrogen fuel cell, or a fuel engine is also installed inside the vehicle to provide driving energy for the land-based unmanned carrier vehicle. A cargo docking platform is arranged on the top of the vehicle body to facilitate cargo transfer with an unmanned aerial vehicle or an unmanned surface vehicle.

[0149] The automatic driving system is used to automatically drive the vehicle to a preset first transfer position.

[0150] In an embodiment of the present invention, an advanced automatic driving system is equipped on the land-based unmanned carrier vehicle, which can drive safely under various road conditions, so that the vehicle can automatically drive to the preset first transfer position corresponding to the intelligent collaborative transportation plan to ensure the safe transportation of the target cargo.

[0151] The first tag identification device is used to identify the electronic tag on the target cargo.

[0152] In an embodiment of the present invention, an identification device corresponding to the electronic tag of the target cargo is equipped on the unmanned vehicle, which can quickly and accurately read the cargo information to ensure the accuracy and traceability of the cargo during the transfer process.

[0153] The cargo docking platform is a robotic arm and / or an automatic transportation device, which is used to transfer the target cargo with an unmanned aerial vehicle or an unmanned surface vehicle.

[0154] In an embodiment of the present invention, a cargo docking platform is provided on the top of the driverless vehicle. When the cargo docking platform is only a robotic arm, in response to the first instruction of the intelligent collaborative transportation plan, the robotic arm is controlled to perform an operation of grasping the target cargo, and the target cargo is carried onto the driverless vehicle or handed over to an aerial transportation drone or a waterborne transportation unmanned boat. When the cargo docking platform is only an automatic transportation device, in response to the first instruction of the intelligent collaborative transportation plan, the automatic transportation device is controlled to perform an operation of transporting the target cargo, and the target cargo is conveyed onto the driverless vehicle or handed over to an aerial transportation drone or a waterborne transportation unmanned boat. When the cargo docking platform is a robotic arm and an automatic transportation device, in response to the first instruction of the intelligent collaborative transportation plan, the robotic arm is controlled to perform an operation of grasping the target cargo and place the target cargo on the automatic transportation device, so as to facilitate the conveyance of the target cargo onto the driverless vehicle or handover to an aerial transportation drone or a waterborne transportation unmanned boat.

[0155] The energy supply device includes a rechargeable battery, a hydrogen fuel cell, and a fuel engine, and is configured to perform an operation of switching the energy supply device in response to an energy switching instruction received from the energy management system, and supply power to the autonomous driving system, the cargo docking platform, and the first tag identification device.

[0156] In an embodiment of the present invention, the energy supply device is communicatively connected to the energy management system, and transmits real-time data of the current energy supply device to the energy management system in real time, and receives an energy switching instruction from the energy management system. In response to the energy switching instruction, an operation of switching the energy supply device is performed. For example, when the current energy supply device is a rechargeable battery, when the current energy consumption of the rechargeable battery reaches a certain threshold, after the energy management system monitors this situation, an energy switching instruction to switch to a hydrogen fuel cell or a fuel engine needs to be issued, and the corresponding operation of switching the energy supply device is performed according to this instruction. Specifically, the energy supply device can supply power to the autonomous driving system, the cargo docking platform, and the first tag identification device.

[0157] Optionally, the intelligent collaborative planning module is further specifically configured to: use the physical data of the target goods, the physical information of the robotic arm, and the environmental data to construct multiple robotic arm cargo handling planning schemes, and form a robotic arm cargo handling planning set; use the shortest handling time, shortest handling path length, and least energy consumption of the robotic arm as the target conditions to construct an objective function; construct constraint conditions according to the physical data of the robotic arm and the environmental data; use the objective function and the constraint conditions to construct a cargo handling model; based on the Grey Wolf algorithm, set the robotic arm cargo handling planning set as the initial wolf pack; input the initial wolf pack into the cargo handling model, and output the fitness values of each grey wolf in the initial wolf pack; determine the alpha wolf, beta wolf, and delta wolf according to the fitness values of each grey wolf, and adjust the positions of each grey wolf based on the fitness value of the alpha wolf to generate an updated wolf pack; count the current number of iterations, and determine whether the current number of iterations is greater than or equal to the second preset iteration threshold; if not, use the updated wolf pack as the new initial wolf pack, and jump to execute the step of inputting the initial wolf pack into the cargo handling model and outputting the fitness values of each grey wolf in the initial wolf pack until the current number of iterations is equal to the second preset iteration threshold, and determine the optimal solution to obtain the optimal robotic arm cargo handling scheme; generate a fourth instruction according to the control instruction corresponding to the optimal robotic arm cargo handling scheme; control the robotic arm to perform the operation of handling the target goods according to the fourth instruction.

[0158] It should be noted that the robotic arm cargo handling planning scheme refers to the initial robotic arm cargo handling planning scheme constructed by analyzing and organizing the physical data of the target goods, the physical information of the robotic arm, and the environmental data.

[0159] The robotic arm cargo handling planning set is the set of all robotic arm cargo handling planning schemes.

[0160] The Grey Wolf Optimizer (GWO) is a meta-heuristic optimization algorithm inspired by the hunting behavior of grey wolf packs.

[0161] The optimal robotic arm cargo handling scheme refers to the optimal solution obtained by solving each robotic arm cargo handling planning scheme in the robotic arm cargo handling planning set using the Grey Wolf algorithm. Among them, the optimal robotic arm cargo handling scheme also belongs to the content of the intelligent collaborative transportation scheme.

[0162] In the embodiments of the present invention, by analyzing and organizing the physical data of the target goods, the physical information of the robotic arm, and the environmental data, multiple robotic arm cargo handling planning schemes are constructed, and a robotic arm cargo handling planning set is constructed using all the robotic arm cargo handling planning schemes.

[0163] Construct a cargo handling model:

[0164] 1) Determine decision variables: Represent the handling path and action sequence of the robotic arm using a set of decision variables. For example, the angles of each joint of the robotic arm, the time points of each action, etc. can be used as decision variables. Assume the robotic arm has n joints, and the angles of each joint at different times form a vector X = [x1, x2,..., x n×m , where m is the number of time steps.

[0165] 2) Define the objective function: The objective function is used to measure the quality of the planning scheme. Multiple factors can be considered, such as the shortest path length, the shortest handling time, the least energy consumption, etc. For example, with the shortest path length as the goal, the objective function f(X) can be defined as the total distance traveled by the end effector of the robotic arm during handling.

[0166] 3) Determine the constraint conditions: Consider the physical constraints of the robotic arm, such as the range limits of joint angles, speed and acceleration limits, etc.; at the same time, environmental constraints, such as avoiding collisions with obstacles, etc., also need to be considered.

[0167] Based on the grey wolf algorithm, set the robotic arm cargo handling planning set as the initial wolf pack. For example, randomly generate a group of grey wolves (solutions), and each grey wolf represents a possible handling path and action sequence planning scheme. Assume the size of the wolf pack is N, then the position vector X i of the i-th grey wolf is = [x i1 , x i2 ,..., x in×m , where i = 1, 2,..., N.

[0168] Input the initial wolf pack into the cargo handling model, and output the fitness values of each grey wolf in the initial wolf pack. Among them, calculate the fitness value of each grey wolf, and the fitness value is determined by the objective function f(X). The smaller the fitness value, the better the planning scheme represented by the grey wolf.

[0169] Determine the alpha wolf, beta wolf, and delta wolf through the fitness values of each grey wolf. Among all grey wolves, select the three grey wolves with the smallest fitness values as the α wolf, β wolf, and δ wolf respectively, which represent the current optimal, sub-optimal, and third-optimal solutions.

[0170] Other gray wolves (ω wolves) update their positions according to the position of the lead wolf, simulating the hunting behavior of the wolf pack. The update process is iterated until the termination condition is met (such as reaching the maximum number of iterations). Specifically, according to the fitness value of the lead wolf, the positions of each gray wolf are adjusted to generate an updated wolf pack; the current number of iterations is counted, and it is judged whether the current number of iterations is greater than or equal to the second preset iteration number threshold; if not, the updated wolf pack is used as the new initial wolf pack, and the process jumps to execute the step of inputting the initial wolf pack into the cargo handling model and outputting the fitness values of each gray wolf in the initial wolf pack until the current number of iterations is equal to the second preset iteration number threshold, and the optimal solution is determined to obtain the optimal mechanical arm cargo handling plan. Among them, the second preset iteration number threshold is set according to the actual situation and is not limited here.

[0171] According to the control instruction corresponding to the optimal mechanical arm cargo handling plan, a fourth instruction is generated; the fourth instruction is transmitted to the mechanical arm, and the mechanical arm responds to the received fourth instruction and performs the operation of handling the target cargo.

[0172] Optionally, the waterborne unmanned boat includes a waterborne unmanned boat body; an environment-friendly power system, an intelligent cargo storage and fixing device, and a second tag recognition device are built in the waterborne unmanned boat body, and a cargo transfer device is also arranged on the waterborne unmanned boat body.

[0173] In the embodiment of the present invention, the hull design of the waterborne unmanned boat takes into account both stability and sailing speed, and an environment-friendly power system is adopted, such as electric propulsion or hybrid power. An intelligent cargo storage and fixing device is arranged inside the cabin, which is convenient for storing and fixing the target cargo. The waterborne unmanned boat is equipped with a recognition device corresponding to the electronic tag of the target cargo, which is convenient for accurately reading the cargo information. The hull is provided with an interface for cargo transfer with the unmanned vehicle and the unmanned aerial vehicle, and a cargo transfer device is arranged at the interface.

[0174] The environment-friendly power system is used to drive the waterborne unmanned boat body to the preset second connection position.

[0175] In the embodiment of the present invention, the environment-friendly power system is such as electric propulsion or hybrid power. The environment-friendly power system is respectively communicatively connected with the energy management system and the intelligent collaborative planning module. The energy management system monitors the real-time state of the environment-friendly power system in real time, and the intelligent collaborative planning module enables the environment-friendly power system to drive the waterborne unmanned boat body to the preset second connection position through the second instruction.

[0176] The intelligent cargo storage and fixing device is used to store and fix the target cargo.

[0177] In the embodiment of the present invention, an intelligent cargo storage and fixing device is arranged inside the cabin of the waterborne unmanned boat body, which is convenient for storing and fixing the target cargo and preventing the cargo from shaking during transportation.

[0178] A second tag identification device for identifying the electronic tag on the target goods.

[0179] In an embodiment of the present invention, an unmanned boat is equipped with an identification device corresponding to the electronic tag of the target goods, which can quickly and accurately read the goods information to ensure the accuracy and traceability of the goods during the transfer process.

[0180] A goods transfer device for transferring the target goods with a land-based unmanned vehicle or an air-based unmanned aerial vehicle.

[0181] In an embodiment of the present invention, an interface for transferring goods with an unmanned vehicle and an unmanned aerial vehicle is provided on the hull of the waterborne unmanned boat body, and a goods transfer device is arranged at the interface. The goods transfer device can be a robotic arm, an automatic transportation device or other transfer devices that can transfer the target goods, supporting automated transfers such as dock robotic arm docking and aerial hovering grasping. The specific transfer device can be installed according to the actual situation and is not limited herein.

[0182] Optionally, the air-based unmanned aerial vehicle includes an air-based unmanned aerial vehicle body; an automatic flight system, a third tag identification device, and a rechargeable battery and / or a fuel power system are arranged inside the air-based unmanned aerial vehicle body. A high-precision positioning system and an intelligent obstacle avoidance device are arranged inside the automatic flight system, and a retractable goods grasping mechanism is arranged at the bottom of the air-based unmanned aerial vehicle body.

[0183] In an embodiment of the present invention, the air-based unmanned aerial vehicle is made of a high-strength and lightweight composite material for the air-based unmanned aerial vehicle body, which has a self-flying system with vertical takeoff and landing and long-distance flight capabilities, and is equipped with a high-precision positioning system and an intelligent obstacle avoidance device. A retractable goods grasping mechanism is installed below the fuselage, which can accurately grasp and place goods. At the same time, a large-capacity battery or a high-efficiency fuel power system is equipped to meet the transportation requirements for different distances. The air-based unmanned aerial vehicle is equipped with an identification device corresponding to the electronic tag of the target goods to facilitate accurately reading the goods information.

[0184] An automatic flight system for driving the air-based unmanned aerial vehicle to a preset third connection position.

[0185] In an embodiment of the present invention, the automatic flight system is communicatively connected to the intelligent collaborative planning module, and the intelligent collaborative planning module uses a third instruction to enable the automatic flight system to perform vertical takeoff and landing and drive the air-based unmanned aerial vehicle to a preset third connection position.

[0186] A third tag identification device for identifying the electronic tag on the target goods.

[0187] In an embodiment of the present invention, the unmanned aerial vehicle is equipped with an identification device corresponding to the electronic tag of the target goods, which can quickly and accurately read the goods information to ensure the accuracy and traceability of the goods during the transfer process.

[0188] It is worth mentioning that appropriate electronic tags and tag recognition devices are selected, and corresponding data processing software is developed to ensure the accurate reading and real-time tracking of cargo information.

[0189] A telescopic cargo grabbing mechanism for grabbing target cargo and handing over the target cargo to a land-based unmanned vehicle or a water-based unmanned boat.

[0190] In the embodiment of the present invention, the telescopic cargo grabbing mechanism is communicatively connected to the intelligent collaborative planning module, and extends downward within a preset distance range according to the third instruction of the intelligent collaborative planning module to facilitate grabbing the target cargo. After grabbing the target cargo, the target cargo is fixed and contracted upward to avoid the telescopic rope for grabbing the target cargo being too long during transportation and colliding with obstacles. When the aerial unmanned vehicle arrives at the end position of the preset third connection position, it extends downward within a preset distance range according to the third instruction of the intelligent collaborative planning module, and releases the target cargo at the connection point of the land-based unmanned vehicle or the water-based unmanned boat or the transportation destination of the target cargo, completing the handover of the target cargo.

[0191] A rechargeable battery and / or a fuel power system for supplying power to the automatic flight system, the high-precision positioning system, the intelligent obstacle avoidance device, the third tag recognition device, and the telescopic cargo grabbing mechanism.

[0192] In the embodiment of the present invention, both the rechargeable battery and / or the fuel power system are communicatively connected to the energy management system, and real-time data of the current rechargeable battery or fuel power system are transmitted to the energy management system in real time, and the energy switching instruction of the energy management system is received. In response to the energy switching instruction, an operation of switching the rechargeable battery or fuel power system is performed. For example, when the current energy supply device is a rechargeable battery, when the current energy consumption of the rechargeable battery reaches a certain threshold, after the energy management system monitors this situation, an energy switching instruction to switch to the fuel power system needs to be issued, and the corresponding operation of switching the energy supply device is performed according to this instruction. Specifically, the rechargeable battery or fuel power system can supply power to the automatic flight system, the high-precision positioning system, the intelligent obstacle avoidance device, the third tag recognition device, and the telescopic cargo grabbing mechanism.

[0193] Optionally, the intelligent obstacle avoidance device is specifically used for: acquiring the first measured distance data of the lidar in the aerial unmanned vehicle body, the image processing estimated distance data of the camera, and the second measured distance data of the millimeter wave radar; performing data fusion processing on the first measured distance data, the image processing estimated distance data, and the second measured distance data based on the Kalman filter algorithm; calculating the obstacle distance estimated value of the first measured distance data, the image processing estimated distance data, and the second measured distance data after data fusion processing; wherein the calculation formula of the obstacle distance estimated value is:

[0194]

[0195] Wherein, d lidar represents the first measured distance data, and d cam represents the distance data estimated by image processing, and d radar represents the second measured distance data; respectively represent the measurement noise variances of the first measured distance data, the distance data estimated by image processing, and the second measured distance data; The aerial vehicle is controlled to avoid obstacles according to the estimated obstacle distance value.

[0196] It should be noted that the first measured distance data refers to the distance data measured by the lidar in the aerial vehicle to measure the distance between the obstacle and the aerial vehicle.

[0197] The distance data estimated by image processing refers to the estimated distance data between the obstacle in the image obtained by processing the obstacle image captured by the camera on the aerial vehicle.

[0198] The second measured distance data refers to the distance data measured by the millimeter wave radar on the aerial vehicle to measure the distance between the obstacle and the aerial vehicle.

[0199] The estimated obstacle distance value refers to the estimated distance value between the obstacle and the aerial vehicle predicted by the Kalman filter algorithm for the first measured distance data, the distance data estimated by image processing, and the second measured distance data.

[0200] In the embodiment of the present invention, by obtaining the first measured distance data, the distance data estimated by image processing, and the second measured distance data measured by the lidar, camera, and millimeter wave radar on the aerial vehicle, the Kalman filter algorithm is used to perform data fusion on the first measured distance data, the distance data estimated by image processing, and the second measured distance data. Assuming that the first measured distance data is d lidar , the distance data estimated by image processing is d cam , and the second measured distance data is d radar , and their respective measurement noise variances are Then the fused estimated obstacle distance value is:

[0201]

[0202] The intelligent obstacle avoidance device can control the aerial vehicle to avoid obstacles according to the estimated obstacle distance value.

[0203] It is worth mentioning that the combined use of multiple sensors such as lidar, cameras, and millimeter-wave radars enables aerial transport drones to perceive the surrounding environment from different dimensions. For example, lidar can provide high-precision distance information, cameras can identify the appearance and texture of objects, and millimeter-wave radars can monitor the motion state of objects in real time. By fusing the data of these sensors, aerial transport drones can understand the surrounding environment more comprehensively and accurately, improving the reliability and accuracy of obstacle avoidance.

[0204] In the embodiments of the present invention, pilot applications are carried out in scenarios such as logistics parks, ports, and urban distribution. For example, in a logistics park, an unmanned vehicle transports the target goods from the warehouse to a designated location within the park, and a drone quickly transports the goods to a farther distribution point, or an unmanned boat transports the goods to the starting point of waterway transportation. Through actual applications in different scenarios, feedback information is continuously collected to improve and perfect the system. Through multiple simulation tests and actual scenario tests, the handover process and device performance are optimized to ensure the safety and efficiency of goods handover.

[0205] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0206] In several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be in an electrical, mechanical, or other form.

[0207] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0208] In addition, in each embodiment of the present invention, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0209] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0210] As described above, the above embodiments are only used to illustrate the technical solution of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of various embodiments of the present invention.

Claims

1. An intelligent land, water and air transportation system, characterized in that, The water, land and air intelligent transportation system includes an intelligent collaborative management system and a land transport unmanned vehicle, an air transport unmanned aerial vehicle and a water transport unmanned boat which are respectively connected to the intelligent collaborative management system in communication; The intelligent collaborative management system is used to formulate and output an intelligent collaborative transportation plan based on the starting and ending locations, physical data, traffic data and environmental data of the target goods; The land transport unmanned vehicle is used to drive the cargo docking platform to receive the target cargo and move to a preset first docking position in response to the received first instruction of the intelligent collaborative transport solution; The unmanned water transport boat is used to respond to the received second instruction of the intelligent collaborative transport solution, start the cargo transfer device to receive the target cargo and move to a preset second docking position; The aerial transport drone is used to drive the retractable cargo grabbing mechanism to grab the target cargo and move it to a preset third docking position in response to the received third instruction of the intelligent collaborative transport solution.

2. The water-land-air intelligent transportation and carrier system according to claim 1, wherein The intelligent collaborative management system includes a data analysis module, an intelligent collaborative planning module and an energy management system; The data analysis module is used to obtain water, land and air coordinated transportation information and pre-process the water, land and air coordinated transportation information; wherein the water, land and air coordinated transportation information includes the starting and ending positions, physical data, environmental data, meteorological data and traffic data of the target goods; The intelligent collaborative planning module is used to formulate an intelligent collaborative transportation plan based on the pre-processed start and end locations, physical data, environmental data, meteorological data and traffic data; The energy management system is used to monitor and switch energy supply equipment.

3. The water-land-air intelligent transportation and carrying system according to claim 2, wherein The intelligent collaborative planning module is specifically used for: Drawing a plurality of initial land, water and air cargo transport routes for coordinated transport by the land transport unmanned vehicle, the air transport unmanned aerial vehicle and the water transport unmanned boat according to the preprocessed start and end positions; Screening each of the initial land, water and air cargo transport routes according to the pre-processed environmental data, meteorological data and traffic data, generating a plurality of updated land, water and air cargo transport routes, and forming a land, water and air cargo transport route set; Based on the genetic algorithm, the set of routes for transporting goods by land, water and air is set as the initialization particle swarm, and the fitness function of each updated route for transporting goods by land, water and air of the initialization particle swarm is calculated; wherein the calculation formula of the fitness function is: Wherein, Length represents the length of the cargo transportation path by land, water and air; WeatherFactor represents the impact factor calculated according to the weather data; TrafficFactor represents the congestion factor calculated according to the traffic data; ChangeCost represents the equipment replacement cost of the land transport unmanned vehicle, the air transport unmanned vehicle and the water transport unmanned boat; w1, w2, w3 and w4 all represent weight coefficients; Performing a selection operation on each of the updated land, water and air cargo transportation routes according to the fitness function values ​​corresponding to each fitness function of the initialized particle swarm, to generate a genetic particle swarm; Performing crossover and mutation operations on each updated land, water and air cargo transport route of the genetic particle group in sequence to generate an updated genetic particle group; Determine whether the current iteration number of updating the genetic particle swarm is greater than or equal to a first preset iteration number threshold; If not, the currently updated genetic particle swarm is set as a new initialized particle swarm, and the step of calculating the fitness function of each updated land, water and air cargo transport route of the initialized particle swarm is jumped to execute until the current iteration number of the currently updated genetic particle swarm is greater than or equal to the first preset iteration number threshold, and the optimal land, water and air cargo transport route is obtained.

4. The water-land-air intelligent transportation and carrying system according to claim 2, characterized in that, The intelligent collaborative planning module is also specifically used for: Determine the type of the land-carrying unmanned vehicle, the type of the air-carrying unmanned aerial vehicle, and the type of the water-carrying unmanned boat according to the preprocessed physical data; Based on the optimal land, water and air cargo transport route, determine a preset first docking position of the land transport unmanned vehicle, a preset second docking position of the air transport unmanned vehicle, and a preset third docking position of the water transport unmanned boat; Formulate an intelligent collaborative transportation plan by using the optimal water, land and air cargo transportation route, the model of the land transport unmanned vehicle, the model of the air transport drone, the model of the water transport unmanned boat, the preset first docking position, the preset second docking position and the preset third docking position; The water, land and air collaborative transportation data in the intelligent collaborative transportation scheme is analyzed, and a first instruction, a second instruction and a third instruction are generated according to the analysis results.

5. The water-land-air intelligent transportation and carrier system according to claim 1, wherein The target goods are provided with an electronic tag for identifying the current location of the target goods.

6. The water-land-air intelligent transportation vehicle system according to claim 2, wherein, The land transport unmanned vehicle comprises a land transport unmanned vehicle body; The land transport unmanned vehicle is provided with an automatic driving system, a first tag recognition device and an energy supply device, and the top of the land transport unmanned vehicle is provided with a cargo docking platform; The autonomous driving system is used to autonomously drive the vehicle to a preset first docking location; The first label recognition device is used to recognize the electronic label on the target goods; The cargo docking platform is a mechanical arm and / or an automatic transport device, which is used to hand over the target cargo to the air transport drone or the water transport unmanned boat; The energy supply device includes a rechargeable battery, a hydrogen fuel cell and a fuel engine, which is used to respond to the energy switching instruction received from the energy management system, execute the operation of switching the energy supply device, and provide power for the automatic driving system, the cargo docking platform and the first tag identification device.

7. The water-land-air intelligent transportation and carrying system according to claim 6, wherein, The intelligent collaborative planning module is also specifically used for: Using the physical data of the target cargo, the physical information of the robotic arm and the environmental data, a plurality of robotic arm cargo handling planning schemes are constructed, and a robotic arm cargo handling planning set is formed; Taking the shortest handling time, the shortest handling path length and the least energy consumption of the robot arm as target conditions, constructing an objective function; Constructing constraint conditions based on the physical data and environmental data of the robotic arm; Using the objective function and the constraint conditions, constructing a cargo handling model; Based on the grey wolf algorithm, the planning set of cargo handling by the robot arm is used as the initialization wolf pack; Input the initialized wolf pack into the cargo handling model, and output the fitness values of each grey wolf in the initialized wolf pack; Determine the lead wolf, the second wolf, and the third wolf according to the fitness values of each grey wolf, and adjust the positions of each grey wolf based on the fitness value of the lead wolf to generate an updated wolf pack; Count the current iteration number, and determine whether the current iteration number is greater than or equal to the second preset iteration number threshold; If not, use the updated wolf pack as the new initialized wolf pack, and jump to execute the step of inputting the initialized wolf pack into the cargo handling model and outputting the fitness values of each grey wolf in the initialized wolf pack until the current iteration number is equal to the second preset iteration number threshold, and determine the optimal solution to obtain the optimal mechanical arm cargo handling plan; Generate a fourth instruction according to the control instruction corresponding to the optimal mechanical arm cargo handling plan; Control the mechanical arm to execute the operation of handling the target cargo according to the fourth instruction.

8. The water-land-air intelligent transportation and carrying system according to claim 1, characterized in that, The waterborne unmanned carrier includes a waterborne unmanned carrier body; An environment-friendly power system, an intelligent cargo storage and fixing device, and a second tag recognition device are built in the waterborne unmanned carrier body, and a cargo transfer device is further arranged on the waterborne unmanned carrier body; The environment-friendly power system is used to drive the waterborne unmanned carrier body to a preset second connection position; The intelligent cargo storage and fixing device is used to store and fix the target cargo; The second tag recognition device is used to recognize the electronic tag on the target cargo; The cargo transfer device is used to transfer the target cargo with the land-based unmanned vehicle or the airborne unmanned aerial vehicle.

9. The water-land-air intelligent transportation and carrier system according to any one of claims 1-8, characterized in that The airborne unmanned aerial vehicle includes an airborne unmanned aerial vehicle body; An automatic flight system, a third tag recognition device, and a rechargeable battery and / or a fuel power system are arranged in the airborne unmanned aerial vehicle body. A high-precision positioning system and an intelligent obstacle avoidance device are arranged in the automatic flight system, and a telescopic cargo grabbing mechanism is arranged at the bottom of the airborne unmanned aerial vehicle body; The automatic flight system is used to drive the airborne unmanned aerial vehicle to a preset third connection position; The third tag recognition device is used to recognize the electronic tag on the target cargo; The telescopic cargo grabbing mechanism is used to grab the target cargo and transfer the target cargo with the land-based unmanned vehicle or the waterborne unmanned carrier; The rechargeable battery and / or the fuel power system is used to supply power to the automatic flight system, the high-precision positioning system, the intelligent obstacle avoidance device, the third tag recognition device, and the telescopic cargo grabbing mechanism.

10. The amphibious, aerial and intelligent transportation and carrier system according to claim 9, characterized in that, The intelligent obstacle avoidance device is specifically used for: Obtain the first measured distance data of the lidar, the image processing estimated distance data of the camera, and the second measured distance data of the millimeter wave radar in the airborne unmanned aerial vehicle body; Based on the Kalman filtering algorithm, perform data fusion processing on the first measured distance data, the image processing estimated distance data, and the second measured distance data; Calculate the obstacle distance estimation value of the first measured distance data, the image processing estimated distance data, and the second measured distance data after data fusion processing; wherein, the calculation formula of the obstacle distance estimation value is: where d lidar represents the first measured distance data, d cam represents the image processing estimated distance data, d radar represents the second measured distance data; respectively represent the measurement noise variances of the first measured distance data, the image processing estimated distance data, and the second measured distance data; Control the aerial vehicle drone to perform obstacle avoidance processing according to the obstacle distance estimation value.

Images