An intelligent unmanned logistics transportation method and system based on optimization efficiency evaluation algorithm

Abstract

The present invention discloses an intelligent unmanned logistics transportation method and system based on an optimization efficiency evaluation algorithm, which relates to the field of intelligent logistics technology, including: using a neural network framework to construct an energy consumption prediction model based on pre-processed comprehensive traffic data to predict the energy consumption of intelligent unmanned logistics vehicles; combining traffic data and the energy consumption prediction results of intelligent unmanned logistics vehicles to dynamically adjust the path planning algorithm; the intelligent unmanned logistics vehicle drives according to the received path instructions, while the on-board system monitors the energy consumption and driving status of the vehicle in real time, and feeds back to the central processing unit in real time; the central processing unit analyzes the received energy consumption and driving status, and adjusts the driving path in real time according to the analysis results. The present invention optimizes path planning and energy consumption strategies through real-time data analysis, and the intelligent unmanned logistics vehicle autonomously selects a low-consumption route, cooperates with on-board monitoring and closed-loop feedback, improves transportation and energy efficiency, and enhances system adaptability and safety.

Description

Technical Field

[0001] The present invention relates to the field of intelligent logistics technology, and in particular to an intelligent unmanned logistics transportation method and system based on an optimized efficiency evaluation algorithm. Background Art

[0002] With the rapid development of the Internet of Things, big data and artificial intelligence technologies, intelligent logistics systems have become a key driver for the transformation and upgrading of the global logistics industry. As an important part of intelligent logistics, intelligent unmanned logistics transportation has received significant attention in recent years. In the face of the growing demand for cargo distribution, traditional logistics transportation methods have exposed problems such as low efficiency, high costs and waste of resources. In order to solve these problems, the intelligent unmanned logistics transportation system came into being. It combines automation, informationization and intelligent technologies to improve the efficiency and reliability of logistics distribution and reduce operating costs.

[0003] Although intelligent unmanned logistics transportation systems have made significant progress, some key challenges still exist. First, most existing systems lack effective real-time energy consumption prediction mechanisms when dealing with complex and changeable urban traffic environments, which may lead to energy waste and inefficient transportation. Secondly, the existing path planning algorithms have limited adjustment capabilities when dealing with sudden traffic conditions, and it is difficult to quickly adapt to environmental changes while ensuring efficiency and accuracy. In addition, the data exchange mechanism between intelligent unmanned logistics vehicles and central processors also has defects, affecting the real-time decision-making ability and stability of the system. Finally, for the energy consumption and driving status information monitored and fed back by the on-board system in real time, the existing technology lacks an effective analysis and adjustment mechanism, making it difficult for unmanned logistics vehicles to adjust strategies in time to optimize energy consumption and path selection when facing dynamic environmental changes. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an intelligent unmanned logistics transportation method and system based on an optimized efficiency evaluation algorithm to solve the problems of energy waste, low transportation efficiency and slow system response caused by the lack of real-time energy consumption prediction, path planning flexibility and efficient data exchange mechanism.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In the first aspect, an embodiment of the present invention provides an intelligent unmanned logistics transportation method based on an optimized efficiency evaluation algorithm, which includes: real-time collection of comprehensive traffic data and preprocessing; using a neural network framework to construct an energy consumption prediction model based on the preprocessed comprehensive traffic data to predict the energy consumption of the intelligent unmanned logistics vehicle; dynamically adjusting the path planning algorithm based on the traffic data and the energy consumption prediction results of the intelligent unmanned logistics vehicle; based on the adjusted path planning algorithm, generating path instructions and energy consumption optimization strategies, and transmitting them to the intelligent unmanned logistics vehicle; the intelligent unmanned logistics vehicle travels according to the received path instructions, and at the same time, the on-board system monitors the vehicle's energy consumption and driving status in real time, and feeds back to the central processor in real time; the central processor analyzes the received energy consumption and driving status, and adjusts the driving path in real time according to the analysis results.

[0008] As a preferred solution of the intelligent unmanned logistics transportation method based on the optimization efficiency evaluation algorithm described in the present invention, the real-time collection of comprehensive traffic data and preprocessing are specifically performed as follows:

[0009] Get real-time video streams of roads through traffic cameras;

[0010] Monitor traffic-related user-posted information through social media;

[0011] Collect weather data through weather stations;

[0012] Intelligent unmanned logistics vehicles use on-board sensors to obtain real-time vehicle status information;

[0013] The collected comprehensive traffic data is cleaned by using anomaly monitoring, data verification and timestamp synchronization;

[0014] The cleaned data are converted into a consistent format through standardization and fused using statistical fusion method to form a comprehensive traffic dataset D.

[0015] As a preferred solution of the intelligent unmanned logistics transportation method based on the optimization efficiency evaluation algorithm described in the present invention, wherein: the energy consumption prediction model is constructed based on the preprocessed comprehensive traffic data set using a neural network framework to predict the energy consumption of the intelligent unmanned logistics vehicle, and the specific steps are as follows:

[0016] CNN and LSTM are used to extract features related to energy consumption prediction from the comprehensive traffic dataset D;

[0017] Based on the features related to energy consumption prediction, an energy consumption prediction model is constructed, and the expression is:

[0018] ;

[0019] Among them, E represents the energy consumption value of the intelligent unmanned vehicle, T is the ambient temperature characteristic, H is the ambient humidity characteristic, Y is the wind speed characteristic, R is the rainfall characteristic, V is the vehicle speed characteristic, L is the load characteristic, S is the traffic condition index, and λ represents the basic energy consumption value when all external conditions affecting energy consumption are in an ideal state. represents the prediction error of energy consumption due to factors that the model fails to capture, α represents the nonlinear effect of temperature on energy consumption, β is the linear coefficient of humidity, and γ is the linear coefficient of wind speed. represents the nonlinear effect of rainfall on energy consumption, η represents the nonlinear effect of speed on energy consumption, is the linear coefficient of the load L, θ is the denominator coefficient of the traffic condition S;

[0020] A loss function is defined to measure the difference between the energy consumption predicted by the energy consumption prediction model and the time energy consumption;

[0021] Based on the weight adjustment of the back-propagation algorithm, dynamic learning rate decay and adaptive batch size adjustment strategies are introduced to minimize the loss function.

[0022] As a preferred solution of the intelligent unmanned logistics transportation method based on the optimization efficiency evaluation algorithm described in the present invention, wherein: the path planning algorithm is dynamically adjusted by combining traffic data and the energy consumption prediction results of the intelligent unmanned logistics vehicle, and the specific steps are as follows:

[0023] The real-time data in the comprehensive traffic data set D and the prediction results E of the energy consumption prediction model are normalized using the minimum-maximum normalization method;

[0024] Based on the results of normalization, a comprehensive path selection function F is defined to calculate the path cost index under the comprehensive starting point q, end point d, traffic conditions S, weather conditions W and predicted energy consumption E. The expression is:

[0025] ;

[0026] Among them, E n is the normalized predicted energy consumption value, S n is the normalized traffic condition index, W n is the normalized comprehensive weather condition index, M n is the normalized path distance, C is a constant used for scale adjustment, σ represents the nonlinear influence of energy consumption on the path cost index G, is the path distance impact adjustment coefficient, τ represents the traffic condition S n The coefficient of influence on the path cost index G, where G represents the path cost index from the starting point q to the end point d;

[0027] Based on the path cost index G, select the path p with the lowest G value from all candidate paths o , the expression is:

[0028] ;

[0029] Among them, G po is the optimal path p after considering all factors o The cost index G, G p represents the cost index G of a specific path p, G p* represents the set of cost indices G of all paths p, G (G p ) represents the comprehensive suitability of path p.

[0030] As a preferred solution of the intelligent unmanned logistics transportation method based on the optimization efficiency evaluation algorithm described in the present invention, wherein: based on the adjusted path planning algorithm, path instructions and energy consumption optimization strategies are generated and transmitted to the intelligent unmanned logistics vehicle, the specific steps are as follows:

[0031] Based on the optimal path p o , construct a series of control signals and generate detailed driving instructions;

[0032] Combined with the energy consumption prediction result E of the intelligent unmanned logistics vehicle and the optimal path p o , dynamically adjust the speed of the intelligent unmanned logistics vehicle and optimize the actual energy consumption of the intelligent unmanned logistics vehicle;

[0033] The generated path instructions and energy consumption optimization strategies are sent to the intelligent unmanned logistics vehicle via wireless networks.

[0034] As a preferred solution of the intelligent unmanned logistics transportation method based on the optimization efficiency evaluation algorithm described in the present invention, wherein: the intelligent unmanned logistics vehicle drives according to the received path instructions, and the vehicle-mounted system monitors the energy consumption and driving status of the vehicle in real time, and feeds back to the central processor in real time. The specific steps are as follows:

[0035] After receiving the command, the intelligent unmanned logistics vehicle decodes the signal through FFT;

[0036] The decoded instructions are parsed using the JSON parsing method, and the control logic is implemented using FPGA to convert the parsed instructions into control signals;

[0037] The vehicle's internal systems communicate via a controller area network to send control signals to the actuators;

[0038] Intelligent unmanned logistics vehicles travel along the designated path according to the autonomous driving system.

[0039] As a preferred solution of the intelligent unmanned logistics transportation method based on the optimization efficiency evaluation algorithm described in the present invention, the central processor analyzes the received energy consumption and driving status, and adjusts the driving path in real time according to the analysis results. The specific steps are as follows:

[0040] In the intelligent unmanned logistics vehicle along the p o While driving, the on-board system monitors the energy consumption and comprehensive traffic data of the intelligent unmanned logistics vehicle in real time, and analyzes the real-time changes of the comprehensive traffic data and the energy consumption of the intelligent unmanned logistics vehicle during driving, especially the traffic flow conditions S and weather conditions W. n changes;

[0041] Once the central processor detects changes in environmental conditions (for example, traffic congestion or worsening weather), the system immediately recalculates the optimal path based on real-time energy consumption and comprehensive traffic data. o At the same time, the costs of all other candidate paths are also re-evaluated and their G values ​​are calculated;

[0042] By comparing the updated path cost index G(p′) of the new path with the path cost index G(p o ) value to adjust the driving path;

[0043] If the path cost index G(p′) of the new path p′ is less than the current optimal path p o The path cost index G (p o ) value, then p′ becomes the new optimal path p o ′;

[0044] If the path cost index G(p′) of the new path p′ is ≥ the current optimal path p o The path cost index G (p o ) value, then keep the current optimal path p o Keep driving.

[0045] In the second aspect, the present invention provides an intelligent unmanned logistics transportation system based on an optimization efficiency evaluation algorithm, including a data fusion and preprocessing module, an energy consumption prediction and optimization module, an intelligent path planning module, a central decision and communication module and an intelligent unmanned logistics vehicle execution module; the data fusion and preprocessing module is used to collect and preprocess comprehensive traffic data to ensure the quality and availability of the data; the energy consumption prediction and optimization module is used to predict energy consumption based on a neural network model, and optimize path selection to reduce energy consumption; the intelligent path planning module is used to dynamically adjust path planning, and generate an optimized path by combining energy consumption prediction and real-time traffic conditions; the central decision and communication module is used to analyze real-time feedback data, adjust path planning and energy consumption strategies, and send update instructions to the unmanned vehicle; the intelligent unmanned logistics vehicle execution module is used to execute path instructions provided by the central processor, while monitoring its own status and providing feedback.

[0046] In a third aspect, an embodiment of the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the intelligent unmanned logistics transportation method based on the optimized efficiency evaluation algorithm as described in the first aspect of the present invention is implemented.

[0047] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the intelligent unmanned logistics transportation method based on an optimized efficiency evaluation algorithm as described in the first aspect of the present invention.

[0048] The beneficial effects of the present invention are as follows: by collecting and preprocessing comprehensive traffic data in real time, building an accurate energy consumption prediction model, and then dynamically adjusting the path planning algorithm, generating the most optimized path instructions and energy consumption strategies, the intelligent unmanned logistics vehicle can autonomously select the driving route with the lowest energy consumption according to real-time data in a complex and changeable environment. At the same time, the energy consumption and driving status are monitored in real time through the on-board system, and a closed-loop feedback mechanism is formed with the central processor to ensure that the path can be adjusted in real time when environmental conditions change, thereby significantly improving the transportation efficiency, energy utilization efficiency and the overall adaptability and safety of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0050] Figure 1 This is a flow chart of the intelligent unmanned logistics transportation method based on the optimization efficiency evaluation algorithm in Example 1.

[0051] Figure 2 This is a flow chart of the intelligent unmanned logistics transportation system based on the optimization efficiency evaluation algorithm in Example 1. DETAILED DESCRIPTION

[0052] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0053] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0054] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0055] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides an intelligent unmanned logistics transportation method based on an optimization efficiency evaluation algorithm, comprising the following steps:

[0056] S1. Collect comprehensive traffic data in real time and perform preprocessing.

[0057] Going a step further, real-time video streams can be obtained through traffic cameras to identify traffic flow, vehicle types, pedestrian activities, etc.

[0058] Through social media, monitor user-posted information related to traffic, such as accident reports and comments on traffic congestion;

[0059] Collect weather data through weather stations, including temperature, humidity, wind speed, rainfall, etc.;

[0060] Intelligent unmanned logistics vehicles use on-board sensors to obtain real-time vehicle status information, including real-time location, speed, load, road conditions, etc.

[0061] Use a secure protocol (HTTPS) to transmit data to the central processor to avoid delays that affect decision-making timeliness, and store data in a database to prevent data loss due to network fluctuations;

[0062] The collected comprehensive traffic data is cleaned by using anomaly monitoring, data verification and timestamp synchronization;

[0063] The cleaned data are converted into a consistent format through standardization and fused using statistical fusion method to form a comprehensive traffic dataset D.

[0064] It should also be noted that anomaly detection: Z-score is used to identify and remove noise or erroneous data, such as outliers caused by sensor failure.

[0065] Data Validation: Checks data integrity and ensures that all required fields have valid values.

[0066] Timestamp synchronization: Use NTP to standardize timestamps on data from different sources to facilitate event correlation.

[0067] Data standardization refers to converting data from different sources and different dimensions to a common scale, which can eliminate the impact of the dimension and make the data comparable. For example, if z-score standardization is used, for each feature, its mean and standard deviation are calculated, and then the mean is subtracted from each data point and divided by the standard deviation to obtain the standardized data. In this way, each feature will have zero mean and unit variance. Make sure that all data fields use the same format and encoding, such as date and time format, numerical precision, etc., to facilitate subsequent data analysis and fusion.

[0068] The statistical fusion method is specifically as follows: find the corresponding data items in different data sets, such as matching vehicle speed data from different traffic sensors. Apply statistical methods to merge these data, such as average, weighted average, median or other more complex statistical models to reduce noise and improve data quality. If there is a data conflict, such as inconsistent data obtained from different sources at the same time point, use appropriate rules or algorithms to decide which data point to use. Integrate all fused data into a new data set D, which contains comprehensive information from all sources and can be used for further analysis and modeling, such as traffic flow prediction, congestion analysis, etc.

[0069] S2. Using a neural network framework, an energy consumption prediction model is constructed based on the preprocessed comprehensive traffic data set to predict the energy consumption of intelligent unmanned logistics vehicles.

[0070] Furthermore, CNN and LSTM are selected to extract features related to energy consumption prediction such as temperature (T), humidity (H), wind speed (Y), rainfall (R), vehicle speed (V), load (L) and traffic conditions (S) from the comprehensive traffic dataset D. CNN extracts image data (such as traffic camera video streams) and LSTM extracts sequence data (such as time series vehicle status);

[0071] Based on the features related to energy consumption prediction, an energy consumption prediction model is constructed, and the expression is:

[0072] ;

[0073] Among them, E represents the energy consumption value of the intelligent unmanned vehicle, T is the ambient temperature characteristic, H is the ambient humidity characteristic, Y is the wind speed characteristic, R is the rainfall characteristic, V is the vehicle speed characteristic, L is the load characteristic, S is the traffic condition index, and λ represents the basic energy consumption value when all external conditions affecting energy consumption are in an ideal state. represents the prediction error of energy consumption due to factors that the model fails to capture, α represents the nonlinear effect of temperature on energy consumption, β is the linear coefficient of humidity, and γ is the linear coefficient of wind speed. represents the nonlinear effect of rainfall on energy consumption, η represents the nonlinear effect of speed on energy consumption, is the linear coefficient of the load L, θ is the denominator coefficient of the traffic condition S;

[0074] It should be noted that the traffic condition index S is calculated through real-time collected road traffic data, including but not limited to real-time video streams captured by traffic cameras, vehicle sensor data, and real-time road condition reports from traffic management departments. These data are input into a special traffic condition assessment algorithm, which comprehensively analyzes information such as traffic flow speed, vehicle density, and traffic light status, and finally outputs an index S that quantifies the degree of traffic congestion. The expression is:

[0075] ;

[0076] Among them, f(v avg ) is a function that maps the average vehicle speed to the interval [0, 1], g(ρ) is a function that maps the vehicle density to the interval [0, 1], where 0 represents the best case and 1 represents the worst case, v avg is the average speed, ρ is the vehicle density, h(τ) maps the traffic light state to the same interval, with a small value when the green light ratio is high and a large value when the red light ratio is high, w v is the weight coefficient of the average speed of the vehicle, w ρ is the weight coefficient of vehicle density, w τ is the weight coefficient of the traffic light;

[0077] The prediction error ι of energy consumption is based on the analysis of historical data. During the model training phase, the prediction error can be calculated by comparing the difference between the model prediction value and the actual observation value. These errors usually follow a certain statistical distribution. By analyzing these distributions, a random variable ι representing the uncertainty of the model prediction can be determined;

[0078] The value of λ is obtained through experimental measurement. In a controlled environment, the vehicle runs under ideal conditions such as static state, no load, and standard ambient temperature. The energy consumption value recorded at this time is the basic energy consumption value λ, which is expressed as:

[0079] ;

[0080] Where N is the number of training samples, E o is the actual observed energy consumption value, i is an index variable used to traverse each sample data point;

[0081] The loss function is defined to measure the difference between the energy consumption predicted by the energy consumption prediction model and the time energy consumption. The expression is:

[0082] ;

[0083] Where N is the number of training samples, E i is the actual energy consumption, is the energy consumption predicted by the model, and L is the difference indicator between the predicted value and the actual value;

[0084] On the basis of adjusting the weights by the back-propagation algorithm, a dynamic learning rate decay and an adaptive batch size adjustment strategy are introduced to minimize the loss function, which is expressed as:

[0085] ;

[0086] Among them, w （t+1） is the weight value of the updated weight vector after the t+1th iteration, w （t） is the weight vector at the tth iteration, η0 is the initial learning rate, t is the number of iterations, τ is the constant of learning decay, ∇L(w （t） ) The instantaneous function L at the current weight w （t） The gradient at

[0087] It should also be noted that CNN feature extraction is specifically as follows: Image processing: environmental data such as temperature T, humidity H, wind speed W, rainfall R, etc. are regarded as image data, and a two-dimensional matrix representation is created, in which each row represents a data point over a period of time, and each column represents a different environmental variable at a specific point in time.

[0088] CNN architecture: Build a CNN model containing convolutional layers, activation layers, pooling layers, and dropout layers to extract spatial features. For example, use convolutional layers to capture local correlations, pooling layers to reduce spatial dimensions, and dropout layers to prevent overfitting.

[0089] Convolutional layer: Set the filter size (such as 3x3 or 5x5), stride, and padding to capture local patterns in the environmental data. For example, the filter can identify periodic changes in temperature and humidity, or the spatial distribution of wind speed and rainfall.

[0090] Activation function: Use ReLU (Rectified Linear Unit) as the activation function to increase the nonlinearity of the model and help learn complex features.

[0091] Pooling layer: Use maximum pooling or average pooling to reduce the size of the feature map while retaining important features and reducing the amount of computation.

[0092] Output: The output of CNN is a multi-dimensional representation of environmental features that can capture spatial patterns in time series.

[0093] The specific LSTM feature extraction is as follows:

[0094] Sequential processing: Input time series data such as vehicle speed V, load L, and road condition S into LSTM, and use the memory unit of LSTM to capture long-term dependencies

[0095] LSTM architecture: Build LSTM units containing input gates, forget gates, cell states, output gates, and possible multi-layer LSTM structures to capture complex time series patterns.

[0096] Input gate: controls what information will be written into the cell state.

[0097] Forget gate: determines which information in the cell state will be discarded.

[0098] Cell state: stores long-term information and is the core of LSTM.

[0099] Output gate: controls which information will be read and output to the next layer.

[0100] Output: The output of LSTM is a dense representation of time series features that can capture long-term dependencies and dynamic changes.

[0101] S3. Combine traffic data and energy consumption prediction results of intelligent unmanned logistics vehicles to dynamically adjust the path planning algorithm.

[0102] Furthermore, the minimum-maximum normalization method is used to normalize the real-time data in the comprehensive traffic dataset D, including temperature (T), humidity (H), wind speed (Y), rainfall (R), vehicle speed (V), load (L) and traffic conditions (S) and the prediction result E of the energy consumption prediction model, and the expression is:

[0103] ;

[0104] Where X is the original parameter value, X max is the maximum possible value of the parameter, X min is the minimum possible value of the parameter;

[0105] Based on the results of normalization, a comprehensive path selection function F is defined to calculate the path cost index under the comprehensive starting point q, end point d, traffic conditions S, weather conditions w and predicted energy consumption E. The expression is:

[0106] ;

[0107] Among them, E n is the normalized predicted energy consumption value, S n is the normalized traffic condition index, W n is the normalized comprehensive weather condition index, including temperature, humidity, wind speed, etc. n is the normalized path distance, C is a constant used for scale adjustment, σ represents the nonlinear influence of energy consumption on the path cost index G, is the path distance impact adjustment coefficient, τ represents the traffic condition S n The coefficient of influence on the path cost index G, where G represents the path cost index from the starting point q to the end point d;

[0108] It should be noted that W n By analyzing historical data, corresponding weights are assigned to each parameter. These weights reflect the importance of their impact on energy consumption. All normalized parameter values ​​are weighted and summed according to their weights to generate a comprehensive weather condition index. The expression is:

[0109] ;

[0110] Where M represents the number of different weather parameters, including temperature, humidity, wind speed, etc., and w j represents the weight of the jth weather parameter, z j represents the normalized value of the jth weather parameter;

[0111] Based on the path cost index G, select the path p with the lowest G value from all candidate paths o , the expression is:

[0112] ;

[0113] Among them, G po is the optimal path p after considering all factors o The cost index G, G prepresents the cost index G of a specific path p, G p* represents the set of cost indices G of all paths p, G (G p ) represents the comprehensive suitability of path p.

[0114] It should also be noted that, through normalization, we ensure that each parameter is in the interval [0, 1], so that they can be added directly without causing a certain parameter to dominate the result due to differences in dimensions or numerical ranges. Then, an appropriate constant C is used to adjust the overall scale to ensure that the range of the function F remains within a reasonable range. For example, C = 4 (i.e., the number of normalized parameters) can be set, so that the theoretical range of the function F is approximately [0, 1];

[0115] The design of the comprehensive path selection function F and the path cost index G is centered on creating a comprehensive evaluation system for intelligent unmanned logistics vehicles to select the best path from multiple candidate paths under changing traffic and environmental conditions. By normalizing key factors such as predicted energy consumption, traffic conditions, weather conditions, and path distance, and assigning appropriate weights, the F function can calculate the comprehensive cost index G for each path. This index not only quantifies the comprehensive performance of the path in terms of energy efficiency, traffic efficiency, and distance, but also takes into account the nonlinear impact of various factors on cost, ensuring the comprehensiveness and accuracy of the evaluation.

[0116] The selection process based on the path cost index G is a system evaluation and decision-making mechanism, the core of which is to select all possible candidate paths from the set p. * In the process, identify and select the path p with the lowest comprehensive cost, that is, the smallest G value o , as the optimal path. The specific process is as follows:

[0117] First, for each candidate path p, its path cost index G(p) is calculated using the comprehensive path selection function defined above. This index takes into account the impact of multiple factors such as predicted energy consumption, traffic conditions, weather conditions, and path distance, and reflects the comprehensive suitability of the path under various conditions. Then, the system traverses all candidate path sets p. * , compare the G value of each path. Finally, the system will select the path p with the smallest G value. o , confirming it as the optimal path under current conditions to guide the driving of intelligent unmanned logistics vehicles.

[0118] S4. Based on the adjusted path planning algorithm, path instructions and energy consumption optimization strategies are generated and transmitted to the intelligent unmanned logistics vehicle.

[0119] Furthermore, based on the optimal path p o , construct a series of control signals and generate detailed driving instructions;

[0120] Combined with the energy consumption prediction result E of the intelligent unmanned logistics vehicle and the optimal path p o , dynamically adjust the speed of the intelligent unmanned logistics vehicle to optimize the actual energy consumption of the intelligent unmanned logistics vehicle. On certain sections of the road, the speed can be reduced to reduce energy consumption, while on other sections, the speed can be increased to save energy by using inertia. For example, when going downhill, the speed can be appropriately increased to store energy using kinetic energy; slow down when approaching traffic lights or before turning to avoid unnecessary braking energy loss;

[0121] The generated path instructions and energy consumption optimization strategies are sent to the intelligent unmanned logistics vehicle via wireless networks.

[0122] It should also be noted that based on the optimal path p o , construct a series of control signals and generate detailed driving instructions. This process usually includes the following key links:

[0123] Path refinement and decomposition: First, the optimal path p o Further refinement, it is broken down into a series of continuous coordinate points or waypoints. These waypoints should be dense enough to accurately guide the vehicle along the preset route, while also taking into account the vehicle's turning radius and acceleration and deceleration characteristics.

[0124] Behavior planning: For each waypoint, determine the specific actions required to reach that point. For example, if the next waypoint requires the vehicle to turn left, then you need to prepare the turning instructions in advance, including details such as when to start slowing down, when to turn the steering wheel, and the speed and angle of the turn.

[0125] Speed ​​planning: Based on road conditions and vehicle performance, plan the vehicle's speed between each waypoint. This includes strategies for acceleration, deceleration, and constant speed driving, as well as how to deal with possible obstacles or emergencies.

[0126] Control signal generation: Convert the above planning into actual control signals, such as the degree of opening and closing of the accelerator / electric switch, braking force, steering angle, etc. These signals will be sent to the vehicle's power system, braking system and steering system to perform specific driving operations.

[0127] Safety Check and Correction: While generating control signals, continuously monitor environmental changes, such as the dynamics of other vehicles, pedestrians or obstacles, and changes in road conditions. Adjust the path or control signal when necessary to avoid collisions or violations of traffic regulations.

[0128] Instruction issuance and execution monitoring: The generated control signal is sent to the vehicle's execution system at an appropriate frequency, and the vehicle's execution status is monitored in real time to ensure that the vehicle drives accurately according to the predetermined instructions.

[0129] S5. The intelligent unmanned logistics vehicle drives according to the received path instructions. At the same time, the on-board system monitors the vehicle's energy consumption and driving status in real time, and provides real-time feedback to the central processor.

[0130] Furthermore, after receiving the command, the intelligent unmanned logistics vehicle decodes the signal through FFT;

[0131] The decoded instructions are parsed using the JSON parsing method, and the control logic is implemented using FPGA to convert the parsed instructions into control signals;

[0132] The vehicle's internal systems communicate via a controller area network, sending control signals to actuators such as motor controllers, power steering systems, and brake systems;

[0133] Intelligent unmanned logistics vehicles travel along the designated path according to the autonomous driving system.

[0134] It should also be noted that after the receiver of the intelligent unmanned logistics vehicle captures the signal, it will use the FFT algorithm to perform spectrum analysis on the signal and identify specific frequency patterns, which correspond to the encoded instruction information. Once the frequency components are identified, the system can apply the inverse process, namely the inverse Fourier transform (IFFT), to restore the frequency domain signal to a digital sequence in the time domain, thereby recovering the original instruction data stream. Subsequently, this data will be further processed and decoded and converted into JSON format to prepare for subsequent instruction parsing.

[0135] Once the signal is decoded and converted into JSON format, the next step is to parse the JSON data to extract the specific driving instruction details. JSON is a lightweight data exchange format that is easy for people to read and write, and easy for machines to parse and generate. The control system on the intelligent unmanned logistics vehicle will use a special JSON parsing library to read this data and convert the JSON format information into structured data, such as objects or arrays, for further processing. After the parsing is completed, a clear set of instructions is obtained, such as "go forward 10 meters" or "turn left 90 degrees".

[0136] S6. The central processing unit analyzes the received energy consumption and driving status, and adjusts the driving route in real time according to the analysis results.

[0137] Furthermore, in the intelligent unmanned logistics vehicle along the p o While driving, the on-board system monitors the energy consumption and comprehensive traffic data of the intelligent unmanned logistics vehicle in real time, and analyzes the real-time changes in comprehensive traffic data (including but not limited to traffic flow, road conditions, traffic light status, weather conditions, etc.) and the energy consumption of the intelligent unmanned logistics vehicle during driving, especially the traffic flow conditions S and weather conditions W.n changes;

[0138] Once the central processor detects changes in environmental conditions (for example, traffic congestion or worsening weather), the system immediately recalculates the optimal path based on real-time energy consumption and comprehensive traffic data. o At the same time, the costs of all other candidate paths are also re-evaluated and their G values ​​are calculated;

[0139] By comparing the updated path cost index G(p′) of the new path with the path cost index G(p o ) value to adjust the driving path;

[0140] If the path cost index G(p′) of the new path p′ is less than the current optimal path p o The path cost index G (p o ) value, then p′ becomes the new optimal path p o ′;

[0141] If the path cost index G(p′) of the new path p′ is ≥ the current optimal path p o The path cost index G (p o ) value, then keep the current optimal path p o Keep driving.

[0142] It should also be noted that real-time monitoring of energy consumption and comprehensive traffic data specifically means that the on-board system of the intelligent unmanned logistics vehicle not only monitors energy consumption, but also collects comprehensive traffic data, including but not limited to traffic flow, road conditions, traffic light status, weather conditions, etc. These data are obtained through on-board sensors and external communication interfaces (such as V2X vehicle-to-external communication). The system needs to analyze these data in real time in order to understand the current traffic conditions and predict future trends.

[0143] Dynamic path replanning is as follows: Once a change in environmental conditions is detected, the central processor should immediately start the path replanning algorithm. This is usually based on some kind of heuristic search algorithm, such as the A* algorithm, which takes into account the estimated cost and the actual cost. The G value reflects the actual cost from the starting point to the current node, including time and energy consumption. When the environment changes, the system recalculates the G value of all candidate paths and evaluates the path cost under the new situation.

[0144] This embodiment also provides an intelligent unmanned logistics transportation system based on an optimization efficiency evaluation algorithm, including: a data fusion and preprocessing module, an energy consumption prediction and optimization module, an intelligent path planning module, a central decision and communication module, and an intelligent unmanned logistics vehicle execution module; the data fusion and preprocessing module is used to collect and preprocess comprehensive traffic data to ensure the quality and availability of the data; the energy consumption prediction and optimization module is used to predict energy consumption based on a neural network model, and optimize path selection to reduce energy consumption; the intelligent path planning module is used to dynamically adjust path planning, and generate an optimized path by combining energy consumption prediction and real-time traffic conditions; the central decision and communication module is used to analyze real-time feedback data, adjust path planning and energy consumption strategies, and send update instructions to the unmanned vehicle; the intelligent unmanned logistics vehicle execution module is used to execute path instructions provided by the central processor, while monitoring its own status and providing feedback.

[0145] This embodiment also provides a computer device, which is suitable for the case of an intelligent unmanned logistics transportation method based on an optimized efficiency evaluation algorithm, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the intelligent unmanned logistics transportation method based on an optimized efficiency evaluation algorithm as proposed in the above embodiment.

[0146] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0147] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the intelligent unmanned logistics transportation method based on the optimization efficiency evaluation algorithm proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0148] In summary, the present invention forms a comprehensive traffic data set in a unified format by collecting and preprocessing comprehensive traffic data in real time, thereby providing a solid foundation for subsequent analysis. Next, a neural network framework is used to extract key features from the data set and construct an energy consumption prediction model. The model carefully considers the impact of environmental conditions, vehicle status and traffic conditions on energy consumption, and achieves high-precision energy consumption prediction through dynamic learning and optimization. Based on these real-time data and prediction results, the system dynamically adjusts the path planning algorithm, calculates the cost index of each path through a comprehensive path selection function, and selects the optimal path with the lowest cost after considering all factors, ensuring the efficient and energy-saving operation of intelligent unmanned logistics vehicles in complex environments, effectively improving logistics efficiency, reducing energy consumption, and enhancing the system's intelligent decision-making capabilities.

[0149] Example 2, referring to Table 1, is the second example of the present invention. To further verify the advancement of the present invention, experimental simulation data of an intelligent unmanned logistics transportation method based on an optimized efficiency evaluation algorithm is provided.

[0150] The experiment selected four different logistics delivery scenarios, named A, B, C, and D, covering delivery tasks in cities, suburbs, rural areas, and severe weather conditions.

[0151] First, we collected comprehensive environmental and vehicle status data through traffic cameras, social media monitoring, weather stations, and intelligent unmanned logistics vehicles. This data covers a wide range of information, including traffic flow, user reports, weather conditions, and vehicle performance.

[0152] Secondly, in-depth data preprocessing work was carried out, including anomaly detection, data verification, timestamp synchronization, and data standardization, which ensured the quality and consistency of the data and laid a solid foundation for subsequent analysis.

[0153] Next, a complex energy consumption prediction model was built using CNN and LSTM, and a dynamic path planning algorithm was implemented. This can not only predict energy consumption, but also adjust the optimal driving path based on real-time data, significantly improving the efficiency and safety of intelligent unmanned logistics vehicles.

[0154] Finally, through signal decoding, command execution and real-time feedback mechanisms, the vehicle's rapid response and adaptation to environmental changes are ensured, and the closed-loop control of the entire experimental process achieves efficient data-driven decision-making and operation.

[0155] The details are shown in Table 1:

[0156] Table 1 Experimental record table

[0157]

[0158] By analyzing the data in the above table, we can clearly see the effectiveness and superiority of the method of the present invention in energy consumption prediction and path planning. For example, in scenario A, compared with the energy consumption predicted by the traditional method of 13.0kWh, the prediction result of the method of the present invention is 12.5kWh, and the actual measured energy consumption is also 12.5kWh, indicating that the prediction error is almost zero, while the traditional method has a deviation of 0.5kWh. This means that under the same conditions, this method can more accurately predict vehicle energy consumption, which helps to achieve more refined cost control and resource allocation.

[0159] Through the intelligent unmanned logistics transportation based on the optimization efficiency evaluation algorithm of the present invention, not only can the error of energy consumption prediction be significantly reduced and the accuracy of prediction be improved, but also the optimal path planning can be quickly made in a dynamic environment, which significantly reduces the processing time and improves the overall logistics efficiency. Especially in the face of complex and changeable traffic conditions and weather conditions, as shown in the table above, in different scenarios, the method of the present invention can maintain a low energy consumption level and a high path planning efficiency, which reflects the innovation and practicality of the present invention in the field of intelligent logistics, as well as its positive contribution to energy conservation, emission reduction and economic efficiency.

[0160] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An intelligent unmanned logistics transportation method based on an optimization efficiency evaluation algorithm, characterized in that: include, Collect comprehensive traffic data in real time and perform pre-processing; Using a neural network framework, an energy consumption prediction model is constructed based on preprocessed comprehensive traffic data to predict the energy consumption of intelligent unmanned logistics vehicles; Combine traffic data with the energy consumption prediction results of intelligent unmanned logistics vehicles to dynamically adjust the path planning algorithm; Based on the adjusted path planning algorithm, path instructions and energy consumption optimization strategies are generated and transmitted to the intelligent unmanned logistics vehicle; The intelligent unmanned logistics vehicle drives according to the received route instructions. At the same time, the on-board system monitors the vehicle's energy consumption and driving status in real time and feeds back to the central processor in real time; The central processor analyzes the received energy consumption and driving status, and adjusts the driving route in real time according to the analysis results; The energy consumption prediction model is constructed based on the preprocessed comprehensive traffic data set using a neural network framework to predict the energy consumption of the intelligent unmanned logistics vehicle. The specific steps are as follows: CNN and LSTM are used to extract features related to energy consumption prediction from the comprehensive traffic dataset D; Based on the features related to energy consumption prediction, an energy consumption prediction model is constructed, and the expression is: ； Among them, E represents the energy consumption value of the intelligent unmanned vehicle, T is the ambient temperature characteristic, H is the ambient humidity characteristic, Y is the wind speed characteristic, R is the rainfall characteristic, V is the vehicle speed characteristic, L is the load characteristic, S is the traffic condition index, and λ represents the basic energy consumption value when all external conditions affecting energy consumption are in an ideal state. represents the prediction error of energy consumption due to factors that the model fails to capture, α represents the nonlinear effect of temperature on energy consumption, β is the linear coefficient of humidity, and γ is the linear coefficient of wind speed. represents the nonlinear effect of rainfall on energy consumption, η represents the nonlinear effect of speed on energy consumption, is the linear coefficient of the load L, θ is the denominator coefficient of the traffic condition S; A loss function is defined to measure the difference between the energy consumption predicted by the energy consumption prediction model and the time energy consumption; Based on the weight adjustment of the back-propagation algorithm, dynamic learning rate decay and adaptive batch size adjustment strategies are introduced to minimize the loss function.

2. The intelligent unmanned logistics transportation method based on the optimization efficiency evaluation algorithm according to claim 1 is characterized in that: The real-time collection of comprehensive traffic data and pre-processing are specifically performed in the following steps: Get real-time video streams of roads through traffic cameras; Monitor traffic-related user-posted information through social media; Collect weather data through weather stations; Intelligent unmanned logistics vehicles use on-board sensors to obtain real-time vehicle status information; Using secure protocols, data is transferred to the central processor; The collected comprehensive traffic data is cleaned by using anomaly monitoring, data verification and timestamp synchronization; The cleaned data are converted into a consistent format through standardization and fused using statistical fusion method to form a comprehensive traffic dataset D.

3. The intelligent unmanned logistics transportation method based on the optimization efficiency evaluation algorithm according to claim 1, characterized in that: The specific steps of combining traffic data and energy consumption prediction results of intelligent unmanned logistics vehicles to dynamically adjust the path planning algorithm are as follows: The real-time data in the comprehensive traffic data set D and the prediction results E of the energy consumption prediction model are normalized using the minimum-maximum normalization method; Based on the results of normalization, a comprehensive path selection function F is defined to calculate the path cost index under the comprehensive starting point q, end point d, traffic conditions S, weather conditions w and predicted energy consumption E. The expression is: ； Among them, E n is the normalized predicted energy consumption value, S n is the normalized traffic condition index, W n is the normalized comprehensive weather condition index, M n is the normalized path distance, C is a constant used for scale adjustment, σ represents the nonlinear influence of energy consumption on the path cost index G, is the path distance impact adjustment coefficient, τ represents the traffic condition S n The coefficient of influence on the path cost index G, where G represents the path cost index from the starting point q to the end point d; Based on the path cost index G, select the path p with the lowest G value from all candidate paths o , the expression is: ； Among them, G po is the optimal path p after considering all factors o The cost index G, G p represents the cost index G of a specific path p, G p* represents the set of cost indices G of all paths p, G (G p ) represents the comprehensive suitability of path p.

4. The intelligent unmanned logistics transportation method based on the optimization efficiency evaluation algorithm as claimed in claim 3 is characterized by: The adjusted path planning algorithm is used to generate path instructions and energy consumption optimization strategies, and transmit them to the intelligent unmanned logistics vehicle. The specific steps are as follows: Based on the optimal path p o , construct a series of control signals and generate detailed driving instructions; Combined with the energy consumption prediction result E of the intelligent unmanned logistics vehicle and the optimal path p o , dynamically adjust the speed of the intelligent unmanned logistics vehicle and optimize the actual energy consumption of the intelligent unmanned logistics vehicle; The generated path instructions and energy consumption optimization strategies are sent to the intelligent unmanned logistics vehicle via wireless networks.

5. The intelligent unmanned logistics transportation method based on the optimization efficiency evaluation algorithm according to claim 4 is characterized in that: The intelligent unmanned logistics vehicle drives according to the received path instructions. At the same time, the vehicle-mounted system monitors the energy consumption and driving status of the vehicle in real time and feeds back to the central processor in real time. The specific steps are as follows: After receiving the command, the intelligent unmanned logistics vehicle decodes the signal through FFT; The decoded instructions are parsed using the JSON parsing method, and the control logic is implemented using FPGA to convert the parsed instructions into control signals; The vehicle's internal systems communicate via a controller area network to send control signals to the actuators; Intelligent unmanned logistics vehicles travel along the designated path according to the autonomous driving system.

6. The intelligent unmanned logistics transportation method based on the optimization efficiency evaluation algorithm according to claim 5 is characterized in that: The central processor analyzes the received energy consumption and driving status, and adjusts the driving path in real time according to the analysis results. The specific steps are as follows: In the intelligent unmanned logistics vehicle along the p o While driving, the on-board system monitors the energy consumption and comprehensive traffic data of the intelligent unmanned logistics vehicle in real time, and analyzes the real-time changes of the comprehensive traffic data and the energy consumption of the intelligent unmanned logistics vehicle during driving; Once the central processor detects changes in environmental conditions, the system immediately recalculates the optimal path based on real-time energy consumption and comprehensive traffic data. o At the same time, the costs of all other candidate paths are also re-evaluated and their G values ​​are calculated; By comparing the path cost index G(p′) of the updated new path with the path cost index G(p o ) value to adjust the driving path; If the path cost index G(p′) of the new path p′ is less than the current optimal path p o The path cost index G (p o ) value, then p′ becomes the new optimal path p o ′; If the path cost index G(p′) of the new path p′ is ≥ the current optimal path p o The path cost index G (p o ) value, then keep the current optimal path p o Keep driving.

7. An intelligent unmanned logistics transportation system based on an optimization efficiency evaluation algorithm, based on the intelligent unmanned logistics transportation method based on an optimization efficiency evaluation algorithm according to any one of claims 1 to 6, characterized in that: Including data fusion and preprocessing module, energy consumption prediction and optimization module, intelligent path planning module, central decision-making and communication module and intelligent unmanned logistics vehicle execution module; The data fusion and preprocessing module is used to collect and preprocess comprehensive traffic data to ensure the quality and availability of the data; The energy consumption prediction and optimization module is used to predict energy consumption based on the neural network model and optimize path selection to reduce energy consumption; The intelligent path planning module is used to dynamically adjust the path planning and generate the optimal path by combining energy consumption prediction and real-time traffic conditions; The central decision-making and communication module is used to analyze real-time feedback data, adjust path planning and energy consumption strategies, and send update instructions to the unmanned vehicle; The intelligent unmanned logistics vehicle execution module is used to execute the path instructions provided by the central processor, while monitoring its own status and providing feedback.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the intelligent unmanned logistics transportation method based on the optimization efficiency evaluation algorithm described in any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the intelligent unmanned logistics transportation method based on the optimization efficiency evaluation algorithm described in any one of claims 1 to 6 are implemented.

Images