Temperature-mass driven path optimization method for whole process of road unmanned vehicle group operation

Abstract

The application is a temperature-mass driven whole process path optimization method for pavement unmanned aerial vehicle group operation, a data set is established through a large number of asphalt mixture cooling test data and an asphalt mixture temperature attenuation curve prediction model is trained to predict the attenuation trend of the asphalt mixture temperature with time, and the temperature attenuation curve is obtained. An intelligent prediction model for predicting the actual asphalt mixture temperature by collecting temperature through a non-contact infrared temperature measurement camera is established to realize real-time monitoring of the asphalt temperature in the compaction operation. According to the obtained asphalt mixture temperature attenuation curve, the best compaction temperature interval and the corresponding best compaction time window are extracted, and the operation section length is divided based on the best compaction time window; when the group performs the operation, the actual temperature of the asphalt at the rolled position is predicted in real time, and the speed of the road roller is adjusted to ensure that the road roller performs the compaction operation in the best compaction temperature interval.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of unmanned road roller fleet, in particular to a temperature-quality driven path optimization method and system for the whole process of road surface unmanned fleet operation. BACKGROUND

[0002] In recent years, with the development of science and technology, many technologies have been gradually applied in engineering machinery, such as unmanned driving technology and positioning technology. Engineering machinery is also developing towards intelligence, digitization and unmanned operation. As an indispensable construction machinery in road compaction, the realization of high-precision and high-efficiency digital unmanned operation of road roller is of great significance to the development of China's highway industry.

[0003] The asphalt material road surface is usually compacted by double steel wheel road rollers. Since the asphalt mixture is very sensitive to compaction degree and temperature, over-compaction or under-compaction, over-heating or over-cooling of the asphalt mixture can lead to unsatisfactory final compaction effect. Therefore, the compaction of the asphalt mixture needs to be completed within the optimal compaction temperature range of the asphalt mixture. The current compaction operation has the following problems: (1) Although there are methods that can roughly predict the time period of the optimal compaction temperature range of the asphalt mixture under different environmental conditions, the temperature of the asphalt mixture within the time period of the optimal compaction temperature range cannot be obtained. Since the on-site construction environmental conditions may change during the operation process, only the time period without the specific asphalt mixture temperature cannot guide the operation of the road roller. (2) The length of the operation section is usually determined by the experience of the driver during the compaction process. Longer operation sections are prone to cause the problem of over-cooling of the asphalt mixture, which leads to reduced compaction quality, while shorter operation sections can lead to low compaction efficiency and excessive fuel consumption of the road roller.

[0004] Therefore, the present application proposes to establish an asphalt mixture temperature decay curve prediction model based on an intelligent prediction algorithm and a real-time monitoring model of the actual temperature of the asphalt mixture during the compaction operation of the road roller. Finally, based on the predicted asphalt mixture temperature decay curve and the real-time predicted actual temperature of the asphalt mixture, the length of the operation section of the unmanned road roller fleet is controlled to meet the actual engineering needs and improve the compaction quality of the asphalt road surface. SUMMARY

[0005] In view of the deficiencies of the prior art, the technical problem to be solved by the present application is to provide a temperature-mass driven path optimization method for the whole process of road unmanned aerial vehicle group operation. A data set is established through a large number of asphalt mixture cooling test data, and an asphalt mixture temperature decay curve prediction model is trained to predict the decay trend of the asphalt mixture temperature with time, and obtain the temperature decay curve. An intelligent prediction model for predicting the actual asphalt mixture temperature by collecting temperature through a non-contact infrared temperature measurement camera is established to realize real-time monitoring of the asphalt temperature during compaction operation. According to the obtained asphalt mixture temperature decay curve, the best compaction temperature interval and the corresponding best compaction time window are extracted, and the operation section length is divided based on the best compaction time window. When the vehicle group is operating, the actual temperature of the asphalt at the rolling position is predicted in real time, and the rolling machine speed is adjusted based on the temperature to ensure that the rolling machine operates in the best compaction temperature interval, and realizes real-time adjustment under unmanned driving condition during compaction process. In addition, the actual time of the last rolling machine completing the operation section is used to optimize the length of the next operation section, and realize real-time adjustment of the operation section length.

[0006] The technical solution adopted by the present application to solve the technical problem is:

[0007] In a first aspect, the present application provides a temperature-mass driven path optimization method for the whole process of road unmanned aerial vehicle group operation, which comprises the following contents:

[0008] Obtain asphalt mixture temperature data under different environmental conditions, and use intelligent prediction algorithm to establish an asphalt mixture temperature decay curve prediction model under different environmental conditions;

[0009] Obtain the surface temperature and actual temperature data of the asphalt mixture outward radiation during compaction operation under different environmental conditions, and use intelligent prediction model to establish an asphalt mixture actual temperature real-time monitoring model, which can obtain the relationship between the surface temperature and actual temperature of the asphalt mixture outward radiation during compaction operation under different environmental conditions, and realize real-time monitoring of the actual temperature inside the asphalt mixture during compaction operation;

[0010] When the vehicle group is operating, the operation section is divided into straight rolling area and lane changing area. When compaction is carried out in the straight rolling area, the actual temperature of the asphalt at the rolling position is predicted in real time by using the asphalt mixture actual temperature real-time monitoring model and recorded and saved. Then, the asphalt mixture temperature decay curve conforming to the on-site environmental conditions is predicted by using the asphalt mixture temperature decay curve prediction model according to the current operation environment, and the best compaction temperature interval corresponding to the best compaction time window T max is determined on the decay curve. The length of the next operation section is determined according to the best compaction time window, and the total operation time T of the vehicle group in any operation section is in the range of: 0.75T max <T<0.9Tmax , at this time T max The temperature attenuation curve determined by the actual temperature data of the asphalt mixture in the previous work section is used to determine the temperature attenuation curve of the asphalt mixture in the first work section, which is generated by predicting the actual temperature data of the asphalt mixture in the pre-work section; under the premise that the speed of the road roller V is constant, the length of the work section is divided according to L = V(T-t2) / q;

[0011] Wherein, L is the length of the straight rolling area in the work section, that is, the length of the work section, t2 is the total time spent on lane changing in the same work section; q is the number of straight rolling lanes that one road roller is responsible for in the work section;

[0012] During actual operation of the fleet, compaction work is carried out according to the divided work sections, and the difference between the actual temperature of the asphalt mixture predicted by the real-time monitoring model and the temperature value at the point predicted by the temperature attenuation curve is compared, a temperature difference threshold is set, and if the difference is greater than the temperature difference threshold, the road roller is accelerated to ensure that the road roller completes the compaction work within the optimal compaction time window.

[0013] Further, the path planning of rolling and lane changing is optimized during the compaction operation of the fleet, the straight rolling area includes a plurality of straight rolling lanes parallel to the road edge, and the number of straight rolling lanes is determined by the road width, the road roller wheel width and the overlapping width of adjacent straight rolling lanes; the lane changing area includes a plurality of curve segments, and a third-order Bezier curve is selected for the lane changing curve, which ensures that the road roller is properly positioned after lane changing, the articulation steering angle is zero, and the entire lane changing path is continuous and smooth, meeting the kinematics and dynamics constraints of the road roller; at the same time, straight rolling and curve lane changing are alternately performed to ensure that the road roller rolls all the asphalt mixture in the work section within a short time;

[0014] Before compaction operation, first, a pre-work section is set for pre-compaction, the optimal compaction speed V of the road roller is determined according to experience, the speed of the road roller is fixed as the optimal compaction speed V, and a speed difference threshold is set, the compaction operation is performed in the pre-work section, the speed difference between the real-time speed during lane changing and the optimal compaction speed is recorded, and the total lane changing time t2 is also recorded, if the speed difference is greater than the speed difference threshold, the lane changing curve of the next work section needs to be optimized to obtain the optimized lane changing curve;

[0015] On each work section, the total operation time t1 of the straight rolling area is determined by T-t2, at this time t2 is the actual total lane changing time of the previous work section, and the length of the current work section is determined according to L = v·t1 / q; the lane changing curves of different rolling lanes in the same work section are the same, the optimization t2 of each work section changes and tends to be shorter, and correspondingly, the length of the straight rolling area becomes larger, thereby optimizing the length of the work section.

[0016] Further, the third-order Bezier curve is composed of a starting point P0, an ending point P3, and two points P1, P2 in the longitudinal driving direction, and the lane changing curve optimization process is: first, the coordinates of P1, P2 are optimized to minimize the difference between the maximum curvature radius and the minimum curvature radius of the planned curve, so that the road roller not only ensures the continuity and smoothness of the lane changing path during the entire lane changing process, but also controls the maximum value of the relative angle between the front and rear bodies of the road roller within a certain range during the lane changing process, thereby ensuring the efficiency of the road roller lane changing; the optimization function of P1, P2 is: J(P1, P2)=k max (t a )-k min (t b ),t a ,t b ∈(0,1),t a ,t b is the value of the Bezier curve when the maximum curvature radius k max and the minimum curvature radius k min are obtained.

[0017] Secondly, if the speed difference between the real-time speed of the road roller and the optimal compaction speed V of the road roller is still greater than the speed difference threshold value after the optimization of the control points P1, P2 during lane changing, it indicates that the lane changing area length is too small, at this time the starting point P0 of lane changing is kept unchanged, the position of the ending point P3 is adjusted to increase the lane changing area length, and the process of optimizing the coordinates of P1, P2 and adjusting the position of the ending point P3 is repeated until the speed difference is controlled within the speed difference threshold value range, and the lane changing area length is increased by 0.5 m each time.

[0018] Further, the asphalt mixture temperature decay curve prediction model comprises an intelligent prediction algorithm and a fitting module, the input of the intelligent prediction algorithm is the environment temperature, the environment humidity and the wind speed, and the output is the asphalt mixture temperature in a future period of time, the intelligent prediction algorithm adopts at least one of LSTM, Transformer, BiLSTM and GRU; the input of the fitting module is the historical asphalt mixture temperature before prediction and the asphalt mixture temperature after prediction, and the output is the decay curve.

[0019] Further, the input of the intelligent prediction model is the environment temperature, the environment humidity, the actual wind speed, the vehicle speed, the surface temperature of the asphalt mixture outward radiation, and the output is the actual temperature of the asphalt mixture; the intelligent algorithm adopts at least one of BP neural network, ANN neural network and RNN neural network.

[0020] In a second aspect, the application provides a temperature-mass driven path optimization system for the whole process of unmanned aerial vehicle group operation on a road surface, comprising a plurality of road rollers, a control module for assisting automatic driving, an upper computer and a decision module, a monocular camera for detecting the road edges on both sides of the road roller to prevent the road roller from driving out of the working area and causing danger, an angle sensor for obtaining the relative rotation angle of the vehicle body, a speed sensor for obtaining the driving speed of the road roller, a temperature and humidity meter for collecting the ambient temperature and humidity, an infrared temperature measurement camera for collecting the surface temperature of the outward radiation of the asphalt mixture, a wind speed sensor for collecting the relative wind speed, and an RTK GNSS for collecting real-time position information of the road roller.

[0021] The upper computer is used to view the real-time operation situation of the vehicle group, including visual display of the compaction of the vehicle group in the working area, compaction parameters of each road roller of the vehicle group, real-time temperature display of the compressed material, and path planning based on the optimal compaction temperature interval.

[0022] The decision module is in wireless communication with the upper computer and can obtain data of the monocular camera, the angle sensor, the speed sensor, the temperature and humidity meter, the infrared temperature measurement camera, the RTK GNSS and the wind speed sensor, and is loaded with an asphalt mixture temperature decay curve prediction model and an asphalt mixture actual temperature real-time monitoring model.

[0023] The asphalt mixture temperature decay curve prediction model is used to predict the asphalt mixture temperature decay curve under different environmental conditions.

[0024] The asphalt mixture actual temperature real-time monitoring model is used to obtain the relationship between the outward radiation surface temperature and the actual temperature of the asphalt mixture during compaction operation under different environmental conditions.

[0025] Further, the decision module is also loaded with a lane changing curve optimization algorithm, which is used to optimize the middle two control points and the end point on the third order Bezier curve according to the speed difference between the set speed and the actual speed of the road roller until the speed difference is controlled within the set speed difference threshold range.

[0026] The length of the straight rolling area of the next working section is determined according to the total lane changing time of the last working section.

[0027] Compared with the prior art, the application has the following advantages:

[0028] 1. The present application establishes an asphalt mixture temperature decay curve prediction model, which can predict the asphalt mixture temperature decay curve under different environmental conditions, and obtain the optimal compaction temperature interval of the asphalt mixture and the corresponding time window. The data source of the curve has two parts, the first part is generated by the real-time collected temperature data of each time period during the operation of the road roller, the second part is generated by the collected temperature data of the asphalt mixture and the environmental factors affecting the temperature drop of the asphalt mixture, and the temperature of the asphalt mixture in the next period is predicted by the asphalt mixture temperature decay curve prediction model; the complete temperature decay curve is fitted by the historical temperature, real-time temperature and predicted temperature. The temperature decay curve can view all temperature data of the whole process of the temperature drop of the asphalt mixture. The length of the subsequent construction operation section is determined by the optimal compaction temperature interval and the corresponding optimal compaction time window of the temperature decay curve; and the temperature at each time point on the curve is compared with the actual measured asphalt temperature during the operation of the road roller, and whether the road roller needs to be accelerated is judged according to the comparison result to guide the compaction operation.

[0029] 2. The present application establishes a real-time monitoring model of the actual temperature of the asphalt mixture during the compaction process of the road roller, considering the temperature, humidity, wind speed, vehicle speed and other environmental factors, which realizes the whole process, continuous, real-time and non-contact monitoring of the actual temperature of the asphalt mixture rolled by the road roller instead of directly using the surface temperature of the asphalt radiation. The road roller collects the surface temperature of the asphalt mixture to be rolled in front or behind by the infrared temperature measurement camera installed on the frame, obtains the current environmental conditions and road roller parameters by the speed sensor, thermometer, infrared temperature measurement camera and wind speed sensor installed on the road roller, and predicts the real temperature of the asphalt mixture inside according to the intelligent prediction model. At the same time, the operation time and the speed of the road roller during operation are displayed in real time on the operation platform, and the speed of the road roller is obtained by the speed sensor. The real temperature of the asphalt to be rolled is compared with the real temperature of the asphalt at the same time point on the temperature decay curve in real time during the operation of the road roller, whether the road roller needs to be accelerated is judged according to the difference, and the compaction operation of the road roller is ensured to be carried out in the optimal compaction time window. According to the above real-time monitoring model of the actual temperature of the asphalt mixture, the real temperature data of the asphalt mixture can be recorded in the whole process and the whole section in each operation section of the road roller, and the data is used to predict the temperature decay curve that meets the site construction conditions by combining the asphalt mixture temperature decay curve prediction model. The temperature decay curve of each operation section is generated in real time by the asphalt mixture temperature data collected in the last operation section. Since there is no previous operation section in the first operation section, a pre-compaction test will be carried out during the formal compaction operation, a pre-operation section length is set, and the asphalt mixture temperature data collected in the pre-operation section is used to predict and generate the asphalt mixture temperature decay curve for guiding the first operation section.

[0030] 3、The application establishes the path planning of rolling and lane changing when the group compacts, and optimizes the path. Due to the material characteristics of asphalt, the compaction of asphalt mixture needs to be carried out in a short time, so it is necessary to reasonably plan the compaction operation path of the unmanned road roller group. When planning the path, the operation section is divided into a straight rolling area and a lane changing area, the straight rolling area includes a plurality of straight rolling lanes parallel to the road edge, the number of the divided straight rolling lanes is determined by the road width, the road roller wheel width and the overlapping width of adjacent straight rolling lanes; the lane changing area includes a plurality of curve segments, the lane changing curve selects a third order Bezier curve, the lane changing curve can ensure that the road roller body is right after lane changing, the hinge steering angle is zero, and the whole lane changing path is continuous and smooth, meeting the kinematics and dynamics constraints of the road roller. At the same time, in order to complete the rolling of the asphalt mixture in a short time, some improvements are made to the path planning, the lane changing after the road roller reciprocating rolling on the previous straight rolling lane is improved to alternating straight rolling and curve lane changing, which can ensure that the road roller rolls all the asphalt mixture in the operation section in a short time. At the same time, the third order Bezier curve is optimized. In actual work, if the relative angle between the front and rear bodies of the road roller is too large, the speed of the road roller will be greatly reduced, therefore, if the relative angle between the front and rear bodies of the road roller is too large during lane changing, the total lane changing time of the road roller will be greatly affected, the construction efficiency is affected and the difficulty of the road roller to complete all the compaction operation in the best compaction temperature interval is increased. Therefore, the lane changing curve of the road roller, i.e. the third order Bezier curve, is optimized, and the coordinates of the control points are optimized, so that the road roller not only ensures the continuity and smoothness of the lane changing path during the whole lane changing process, but also controls the maximum relative angle between the front and rear bodies of the road roller within a certain range during the lane changing process, ensuring the efficiency of the road roller lane changing.

[0031] 4、The application accurately determines the asphalt mixture paving length of each operation section according to the two intelligent prediction methods and the compaction parameters of the road roller, and ensures the quality and efficiency of the compaction operation. According to the temperature decay curve of the asphalt mixture, the best compaction temperature interval of the asphalt mixture and the corresponding time window can be obtained, the length of each operation section is pre-divided according to the time window of the road roller, the total time of the operation time of the group in any operation section is T, T is taken according to a certain proportion of the maximum compaction time window T max , and T is set as t1+t2, wherein t1 is the total operation time of the road roller in the straight rolling area, and t2 is the total time spent by the road roller in lane changing, the preset lane changing length and the control point coordinates of the lane changing curve can obtain the initial lane changing curve, the road roller uses this curve for lane changing when pre-operating the operation section, records the total lane changing time t2 and calculates t1, and according to t1, the length of the operation section is determined. BRIEF DESCRIPTION OF DRAWINGS

[0032] Figure 1 An unmanned road roller fleet asphalt mixture operation path schematic diagram.

[0033] Figure 2 An asphalt mixture temperature attenuation curve schematic diagram.

[0034] Figure 3 A road roller lane changing curve generation schematic diagram.

[0035] Figure 4 A flowchart of the temperature-mass driven road surface unmanned fleet operation whole-process path optimization method of the present application. DETAILED DESCRIPTION

[0036] The specific embodiments of the present application are given below. The specific embodiments are only used to further illustrate the present application and are not limited to the protection scope of the present application.

[0037] The present application provides a temperature-mass driven road surface unmanned fleet operation whole-process path optimization system, which can adjust the unmanned road roller fleet operation path in real time according to the asphalt mixture temperature change, and realize unmanned intelligent high-precision operation.

[0038] The system comprises a road roller subsystem, a construction personnel operation subsystem and a paver control subsystem, and the road roller subsystem comprises a control module, a sensing module, a decision module and a transmission module.

[0039] The road roller subsystem: 1, control module. The control module of the road roller refers to the power-assisted device installed on each actuator of the road roller. The power-assisted device is directly connected to the decision module and is controlled by the decision module. The actuators used by the road roller during operation include gear shift actuators, steering actuators, throttle actuators, brake actuators, ignition and vibration switch actuators.

[0040] The gear shift actuator uses a stepper motor as an additional power-assisted device, which relies on the motor torque to drive the gear shift push rod to rotate, thereby realizing the gear shift function.

[0041] The steering actuator uses an electric steering wheel to replace the original steering wheel.

[0042] The throttle actuator and the brake actuator use power-assisted devices such as electric push rods to drive the throttle push rod and the brake pedal, thereby realizing speed adjustment and brake operation.

[0043] The ignition and vibration switch actuators use relays to control the switches, including the ignition switch, the vibration switch and the large vibration switch.

[0044] 2、Sensing module mainly includes: 1) RTK GNSS. Used for collecting real-time position information of the road roller, composed of GNSS base station and GNSS flow station, realizing differential solution. 2) Monocular camera. Monocular camera is fixed on both sides of the road roller cab, used for detecting the two sides of the road to prevent the road roller from driving out of the working area and danger. 3) Laser radar. Laser radar is installed at the front end of the front frame and the rear end of the rear frame, used for detecting surrounding obstacles, and transmitting obstacle information to the decision module, and the decision module judges and makes corresponding operation. 4) Angle sensor. The angle sensor is installed at the hinge connection between the front frame and the rear frame of the road roller, used to obtain the relative angle of the vehicle body and transmit the data to the decision module for analysis and calculation, used for path tracking control of the road roller, and the communication protocol is RS485 protocol. 5) Speed sensor. Used to obtain the driving speed of the road roller.

[0045] 3、The decision module is a road roller control board card, which integrates the interfaces of the devices of the above-mentioned sensing module and the execution mechanism control device, and the main control adopts an stm32 single-chip microcomputer. The board card is the "brain" of the whole unmanned road roller, and all judgments and corresponding decisions are made on the board card.

[0046] 4、The transmission module adopts a wireless transmission module, including an antenna, which is placed on the top of the road roller cab and communicates with the host computer through a virtual serial port.

[0047] The construction personnel operation subsystem (host computer) is a PC end page, which can be used for checking the real-time operation condition of the machine group, mainly including visual display of the machine group compaction in the working area, compaction parameters of each road roller of the machine group, real-time temperature display of the compacted material, and path planning based on the best compaction temperature interval.

[0048] The application provides a temperature-mass driven road surface unmanned machine group operation whole process path optimization method, which specifically comprises the following steps:

[0049] Step 1, establishing an asphalt mixture temperature attenuation curve prediction model.

[0050] Firstly, the environmental conditions that may affect the temperature of the asphalt mixture are selected, mainly including environmental temperature, environmental humidity, wind speed and the like, then through a large number of tests, the amplitude and value of the temperature drop of the asphalt mixture with time under different environmental conditions are collected; the corresponding asphalt mixture temperature under different environmental temperatures, environmental humidities and wind speeds is obtained, a first data set composed of environmental temperature, environmental humidity, wind speed and asphalt mixture temperature is divided into training data and test data, 75% of the sample data is used as the training set, 25% of the sample data is used as the verification test set, and the training set and the verification test set are randomly divided;

[0051] In this embodiment, a Long Short-Term Memory Neural Network (LSTM) is used as the basic model for the intelligent prediction algorithm to establish a prediction model for the temperature decay curve of asphalt mixture. The process of obtaining the prediction model for the temperature decay curve of asphalt mixture is as follows:

[0052] (1) Normalize both the training and test data. The normalization formula is: Where max represents the maximum value of each influencing factor in the sample data, min represents the minimum value of each influencing factor in the sample data, and x represents the sample data. * The data is the normalized sample data;

[0053] (2) Ambient temperature, humidity, and wind speed are used as inputs, and the asphalt mixture temperature over a future period is used as the output. The LSTM model has 3 input layer neurons and 1 output layer neuron. The number of hidden layer neurons is not fixed and needs to be determined by trial and error. By substituting the number of neurons from 1 to 50, the error results under each condition are compared, and the number of hidden layer neurons with the best prediction result is selected. The learning rate is set to 0.02, and the number of iterations is 150. During the establishment of the LSTM model, the LSTM function library provided in MATLAB is used to analyze W. f W i W c Wo equal weight matrix and b f b i b c b o The bias terms are randomly initialized, and then the Adam optimization algorithm is used to iteratively update and adjust the model weights so that the network can learn better and faster.

[0054] (3) The model is trained using the training set and validated using the validation test set to obtain the trained LSTM model. The asphalt mixture temperature measured on-site for a period of time is input, and the asphalt mixture temperature for a future period of time is predicted using the trained LSTM model. The asphalt mixture temperature is then fitted with the input asphalt mixture temperature for a period of time in the fitting module to obtain the temperature decay curve of the asphalt mixture.

[0055] The LSTM model and fitting module together constitute a prediction model for the temperature decay curve of asphalt mixtures, which is used to predict the temperature decay trend of asphalt mixtures.

[0056] Step 2: Establish a real-time monitoring model for the actual temperature of the asphalt mixture during compaction operations.

[0057] (1) Install speed sensor, hygrometer, contact temperature probe, infrared temperature measurement camera and wind speed sensor on the road roller. The speed sensor is installed on the steel wheel of the road roller to collect real-time vehicle speed; the hygrometer is installed on the roof of the road roller to collect the ambient temperature and humidity of the current construction; the contact temperature probe is installed on the bottom of the road roller frame through a guide rail and a motor to collect the actual temperature of the asphalt mixture. The motor can drive the guide rail to move up and down, and the contact temperature probe is installed on the guide rail. When temperature measurement is needed, the guide rail is vertically lowered to drive the probe into the asphalt mixture. When driving normally, the probe is retracted to prevent it from being damaged too quickly. The infrared temperature measurement camera is installed on the bottom of the road roller frame to collect the outwardly radiating surface temperature of the asphalt mixture. The wind speed sensor is installed on the roof of the road roller to collect the wind speed. It should be noted that since the wind speed sensor is installed on the road roller, it measures the relative wind speed of the wind speed and the vehicle speed. Therefore, the actual wind speed is obtained by combining the vehicle speed measured by the speed sensor. Then, multiple sets of data are collected and processed, each set of data including the actual wind speed, ambient temperature and humidity, actual temperature of the asphalt mixture, and outwardly radiating surface temperature of the asphalt mixture.

[0058] (2) Construct an asphalt mixture actual temperature real-time monitoring model. First, standardize all the collected data to 0-1, and construct a second data set in groups and divide it into a training set and a test set. The training set accounts for 75%, and the test set accounts for 25%. Second, use a BP neural network to construct an asphalt mixture temperature actual temperature monitoring model. The input layer node number of the BP neural network is five, which is the ambient temperature, ambient humidity, actual wind speed, vehicle speed, and outwardly radiating surface temperature of the asphalt mixture. The output layer node number of the BP neural network is one, which is the actual temperature of the asphalt mixture. The hidden layer is one layer, and the number of hidden layer nodes is calculated according to the empirical formula wherein l is the number of hidden layer nodes, m is the number of input layer nodes, n is the number of output layer nodes, and a is a constant between 1 and 10. According to the formula, the number of hidden layer nodes is 3-12, which is preliminarily selected as 10 in this embodiment to obtain the basic architecture of the BP neural network. Third, train the BP neural network. The training set divided from the second data set is input into the BP neural network for training to obtain the predicted value of the actual temperature of the asphalt mixture. The output error of each layer of neurons is calculated through an error function for back propagation, and then the weight and threshold of each layer of neurons are adjusted according to the error function.

[0059] The error function is defined as follows: Let the number of learning samples be P, and the input of the i-th sample be x 1 ,x 2 ,...x pThe learning samples are input into the BP neural network, and the output The BP neural network algorithm generally adopts a square error function as the objective function of the neural network. At this time, the error E p of the pth learning sample can be expressed as: wherein, is the expected output of the pth learning sample, y k is the actual temperature of the asphalt mixture corresponding to the learning sample.

[0060] The global error of the P learning samples can be further obtained, and the calculation formula is:

[0061] m is the number of input layer nodes, n is the number of output layer nodes, n = 1 in the embodiment, and P is the number of learning samples.

[0062] After the error function is determined, the weights and thresholds of the output layer and the hidden layer can be changed according to the gradient descent method, and the error limit value E min is set. min When E < E min , the training is stopped, which indicates that the training error meets the requirements and the training effect is good; if E ≥ E min , the training is continued until E < E min , and the trained BP neural network model is obtained, that is, the asphalt mixture actual temperature real-time monitoring model.

[0063] (3) The relationship between the temperature collected by the infrared temperature camera and the temperature collected by the contact temperature probe is established by applying the asphalt mixture actual temperature real-time monitoring model, that is, the relationship between the surface temperature of the asphalt mixture outward radiation and the actual temperature is established. The asphalt mixture actual temperature real-time monitoring model is stored in the construction personnel operation subsystem of the unmanned road roller fleet, and is used to monitor the real-time actual temperature of the asphalt mixture in the compaction process; during the unmanned operation of the road roller, no contact temperature probe is set, the surface temperature of the asphalt mixture outward radiation is collected by the infrared temperature camera, and is used as the input of the asphalt mixture actual temperature real-time monitoring model; the actual wind speed, vehicle speed, environment temperature and environment humidity are obtained according to the working environment, and then the actual temperature of the asphalt mixture at the temperature measuring point is output according to the asphalt mixture actual temperature real-time monitoring model, so as to realize the real-time temperature monitoring in the compaction operation.

[0064] Step 3, according to the asphalt mixture temperature decay curve and the optimal compaction temperature interval, the optimal compaction time window T max is determined, and then the path planning is performed to divide the operation section length.

[0065] Asphalt mixture is very sensitive to the degree and temperature of compaction. If compaction is carried out at a temperature higher or lower than the threshold value (i.e. outside the optimum compaction temperature interval), it can result in an ideal layer density / thickness that cannot be achieved, or even premature failure.

[0066] Based on the monitored actual temperature of the asphalt mixture obtained in step 2, the asphalt mixture temperature decay curve prediction model obtained in step 1 is input to predict the asphalt mixture temperature decay curve that meets the field environmental conditions.

[0067] The optimum compaction temperature threshold value is determined according to construction experience, and the range between the upper and lower limits of the optimum compaction temperature threshold value is the optimum compaction temperature interval;

[0068] The optimum compaction time window T corresponding to the optimum compaction temperature interval is found on the asphalt mixture temperature decay curve that meets the field environmental conditions. max (see Figure 2 ).

[0069] Due to the long time of the roller operation, the operating environmental conditions can change at any time, resulting in different temperature decay rates of the asphalt mixture, so different operation sections can have different asphalt mixture temperature decay curves. In order to more accurately obtain the temperature decay curve of the asphalt mixture, the actual temperature of the asphalt mixture during the operation of the roller is collected in real time, and the temperature decay curve of each operation section is generated in real time from the asphalt mixture temperature data collected in the previous operation section. Since there is no previous operation section in the first operation section, a pre-compaction test will be carried out when the formal compaction operation is carried out, a pre-operation section length is set, and the asphalt mixture temperature data collected in real time in the pre-operation section is used to predict and generate the asphalt mixture temperature decay curve for guiding the first operation section. The specific implementation is as follows:

[0070] Before the operation of the first operation section, a pre-operation section is set, and the roller carries out the compaction operation of the pre-operation section after the paving machine finishes discharging. During the operation, the roller obtains the outward radiation surface temperature of the asphalt mixture through the infrared temperature measurement camera, then the actual temperature of the asphalt mixture is obtained in real time by using the asphalt mixture actual temperature real-time monitoring model, and the data is recorded and uploaded to the construction personnel operation subsystem.

[0071] Since the compaction operation needs to be carried out within the optimum compaction temperature interval of the asphalt mixture, the above measured data is not complete, so the actual temperature of the asphalt mixture measured by the asphalt mixture actual temperature real-time monitoring model is input into the asphalt mixture temperature decay curve prediction model to predict the temperature of the asphalt mixture in the next period of time, and the temperature decay curve is completed. The optimum compaction temperature interval and the time window of the first operation section are determined according to the temperature decay curve.

[0072] The real-time actual temperature data of the asphalt mixture is predicted by the real-time monitoring model of the asphalt mixture actual temperature during the operation of the first operation section, and is recorded, so as to predict the temperature of the asphalt mixture in the next period of time according to the asphalt mixture temperature decay curve prediction model, generate a new temperature decay curve, determine the optimal compaction time window of the second operation section according to the new temperature decay curve, guide the construction of the second operation section, and so on until the operation is completed.

[0073] During the compaction operation of the asphalt mixture, the area is first divided, and the compaction area is divided into each compaction sub-area according to the number of road rollers, and the subsequent machine group will independently perform the compaction operation in each compaction sub-area.

[0074] After dividing each compaction sub-area, path planning is performed for each road roller in each compaction sub-area, and the path planning includes path planning of the straight rolling area and the lane changing area. Since the asphalt mixture to be compacted is temperature sensitive, the path planning is planned according to the time window. It is assumed that the total operation time of a straight rolling area in an operation section is t1, the total time of a lane changing area is t2, and the total operation time of an operation section is T, T=t1+t2. Then T max , T max is the optimal compaction time window of the asphalt mixture under the current environmental conditions. If the total operation time T of an operation section exceeds T max , it means that the compaction operation in the optimal compaction temperature interval of the asphalt mixture is not completed, which may cause quality problems in the part that is not compacted in the optimal compaction temperature section. Therefore, it is necessary to ensure that the compaction time period of the entire operation section is completed within the optimal compaction time window. However, T that is too close to or too conservative may have some problems. If T is too close to T max , the time loss caused by some unknown factors in the machine group operation may cause the final compaction time of the operation section to exceed T max , which is not desirable. Therefore, T is set to be less than 0.9T max ; if T is set too conservatively, the length of the straight rolling area of each operation section may be too short, the number of operation sections may be too large, and the total compaction time may increase. If the length of the straight section operation is too small, the road roller will frequently change lanes, which will reduce the construction efficiency and increase the fuel consumption. Therefore, in order to save time and reduce the fuel consumption of the road roller, the minimum straight section operation length should be set for each operation section to ensure that T>0.75T max ; therefore, the range of the finally set T is: 0.75T max <T<0.9T max .

[0075] For a certain operation section, T max is a certain value, and T is a certain multiple of T max .For the pre-work section, take T = 0.85T max , T = t1 + t2, Wherein L is the length of the straight rolling area in the work section, that is, the length of the work section; V is the speed of the roller; q is the number of straight rolling lanes in the work section responsible for by one roller.

[0076] The lane changing curve is a third-order Bezier curve, and the total lane changing time is affected by the lane changing length, the lane changing width and the control points of the Bezier curve. In the pre-work section, the lane changing length, the lane changing width and the control point coordinates of the lane changing region are given first, and in the work process of the pre-work section, it is judged whether the lane changing curve needs to be optimized, and the total lane changing time t2 is recorded, which is used to calculate t1, and then L is calculated according to the above formula. If the lane changing curve needs to be optimized, the optimized lane changing curve is applied to the next work section, and the total lane changing time t2 is recorded again.

[0077] Assuming that the area for path planning is a rectangular area, the rectangular area is divided into straight rolling areas and lane changing areas through path planning, the straight rolling areas include a plurality of parallel rolling strips, and the lane changing areas include a plurality of lane changing curves, the lane changing curves connect two adjacent straight rolling areas (see Figure 1 ). In traditional work compaction, the roller is reciprocatingly rolled on one rolling strip, and after the rolling of the strip is completed, lane changing is performed to the next strip for rolling. However, due to the material characteristics of the asphalt mixture which is easy to cool, the use of this method for rolling will lead to reduced efficiency and consume a large amount of time, and the unrolled strip at the rear is easy to cool, which affects the compaction quality. Therefore, two lane changing areas are planned during path planning, which are located at the starting position and the terminal position of the work section respectively, the starting position is lane changing 1 area, and the terminal position is lane changing 2 area. The work of the roller will be carried out alternately according to straight work-lane changing-straight work, that is, straight rolling of the first strip is carried out first, then lane changing is performed in the lane changing 2 area, after lane changing to the second rolling strip, straight rolling is continued, after rolling to the lane changing 1 area, lane changing is performed, after lane changing to the third rolling strip, straight rolling is continued, and so on, until all the rolling strips in the compaction partition of the roller are compacted, and the compaction work of the work section is completed.

[0078] In detail, in step three. The lane changing region curve selects a Bezier curve. The n-order Bezier curve B(t) of the given points P0, P1, …, P n can be expressed in the general form as shown in the formula:

[0079]

[0080] The lane changing curve of the application adopts a third-order Bezier curve, and the control points are P0, P1, P2 and P3. The formula of the third-order Bezier curve in the two-dimensional plane rectangular coordinate system is:

[0081]

[0082] wherein (x i ,y i ) are the coordinate information of each control point selected, and three-order Bezier curve needs four control point coordinates. y is the lateral displacement of the driving during the lane changing process (perpendicular to the straight rolling direction), x is the longitudinal displacement of the driving during the lane changing process (straight rolling direction); t is the curve parameter.

[0083] According to the coordinate of the control point, a lane changing curve is generated, and the initial control point coordinates will select the lane changing starting point coordinate P0, the lane changing ending point coordinate P3, and two midpoint coordinates (P1, P2) on the longitudinal driving direction line, and the position of the coordinate point will be adjusted subsequently to obtain a lane changing curve with a more optimal solution.

[0084] Step 4: The machine group performs the compaction operation, and after the compaction operation of the current operation section is completed, the asphalt mixture temperature decay curve under the current environmental condition is predicted according to the asphalt mixture temperature data recorded and saved by the operation section, and the optimal compaction time window of a new operation section is re-determined according to the temperature decay curve, so as to optimize the operation length of the new operation section.

[0085] The unmanned operation of the roller group is completed through the cooperation of each subsystem, and the specific steps are as follows: 1. Coordinate collection. The operator collects the coordinates of the four corner points of the rectangular compaction area and inputs them into the operator subsystem, and the operator subsystem converts the collected latitude and longitude coordinates into two-dimensional plane rectangular coordinates through the Gauss-Kruger orthographic projection calculation method. All subsequent collected coordinates will be converted into this projection coordinate. 2. Region division. After inputting the four corner point coordinates into the operator subsystem, the rectangular compaction area will appear on the page. Then the compaction partition is divided, and the compaction area is divided into the same number of compaction partitions as the number of rollers along the compaction direction, and the length and width of each compaction partition are equal. 3. Determine the length of the operation section. The compaction area is divided into several operation sections along the direction of the roller, and the length of the operation section currently requiring compaction operation is determined by the temperature decay curve generated by the real-time temperature data of the asphalt mixture monitored by the real-time monitoring model. If it is the first operation section, the temperature decay curve generated by the pre-operation section asphalt mixture temperature data is used to determine the length of the operation section. 4. Path planning. The path of each compaction partition of the first operation section is planned. According to the compaction partition width, roller width, and adjacent compaction strip overlap distance, several parallel compaction strips are divided for all compaction partitions, and lane change area 1 and lane change area 2 are set at the beginning and end of the operation section, and the lane change curve equation is obtained according to the initial lane change parameters and point positions. At this time, the operator subsystem will obtain the straight line equation of all compaction strips, the curve equation of the lane change curve, and a large number of coordinate point positions on the straight line and the curve. The operator subsystem will transmit the equations and point positions to the decision module through the transmission module, and through the data transmission of the sensing module and the calculation of the decision module, the roller will be controlled to operate according to the given route. 5. Paver discharging. After path planning, the compaction operation begins, and the paver first enters the site to pave the asphalt mixture. The paver is equipped with a positioning module and a control module to control its own operation. After the paver discharges to the length L of each operation section, it stops discharging. The movement direction, trajectory, and distance of the paver, as well as the temperature of the asphalt mixture, can be displayed on the operator subsystem. 6. Group compaction operation. After discharging, the group begins to enter the site for compaction operation. The group operates according to the given path of the path planning, and all parameters of the roller and the compressed material during operation are displayed and saved on the operator subsystem interface for subsequent path optimization. The roller parameters mainly include: roller speed, vibration frequency, body relative angle, lateral error, heading error, and angle error; the parameters of the compressed material mainly include: predicted temperature of the material temperature decay curve, and actual temperature of the asphalt mixture predicted by the infrared temperature camera using the actual temperature real-time monitoring model. 7. Control of group operation.The construction personnel operating subsystem controls the fleet operation. The temperature decay curve can reflect the change rule of the asphalt mixture temperature over time at the present time or in the near future, but the environmental conditions can change at any time. Therefore, the difference between the actual asphalt mixture temperature predicted by the asphalt mixture actual temperature real-time monitoring model and the temperature value at the corresponding time point on the temperature decay curve is used to determine the change of the current environment, so as to control the fleet operation. For example, if the temperature predicted by the asphalt mixture actual temperature real-time monitoring model is less than the temperature value at the point on the temperature decay curve, and the difference is too large, it indicates that the change of the current environment has accelerated the cooling of the asphalt mixture, and the road roller is accelerated to ensure that the road roller completes the compaction operation within the optimal compaction time window.

[0086] The lane changing area will also optimize the path. According to practice, the larger the relative turning angle of the road roller during turning, the slower the speed of the road roller, which leads to an increase in the total lane changing time. Therefore, if it is found that the speed of the road roller during lane changing is much smaller than the speed during normal operation, it indicates that the lane changing curve is unreasonable, and optimization is needed to ensure that the lane changing curve is relatively smooth and the curvature change of the curve is small. Continuously adjusting the control points of the Bezier curve can change the curve equation to achieve the desired smooth effect. Fixing the two end points P0 and P3 of the third-order Bezier curve, changing the two middle points of the third-order Bezier curve, and finally obtaining a trajectory that satisfies the kinematic constraints, initial pose state constraints, target pose state constraints, and curvature continuity constraints. By solving the optimal parameters that satisfy the above conditions, the optimal trajectory is found.

[0087] The optimization function used is: J(P1, P2) = k max (t a )-k min (t b ), t a , t b ∈(0, 1), t a , t b is the value when the Bezier curve reaches the maximum and minimum curvature radii, and k represents the curvature radius.

[0088] The physical meaning represented by the optimization function is to optimize the parameters P1 and P2 so that the difference between the maximum and minimum curvature radii of the planned curve is minimized, thereby ensuring that the obtained curve trajectory is relatively smooth.

[0089] If the speed of the road roller still differs from the normal driving speed of the road roller when changing lanes is found, it indicates that the length of the lane changing area is too small. In this case, the starting point P0 of the lane changing is kept unchanged, the position of the end point P3 is adjusted to increase the length of the lane changing area, and the above process is repeated to optimize P1 and P2, and the length of the lane changing area is increased by 0.5 m each time.

[0090] In the present application, the optimized lane changing curve obtained from the data of the previous work section is used in the next work section. When working according to the optimized lane changing curve, the speed difference between the real-time speed and the optimal compaction speed during lane changing is recorded, and the total lane changing time t2 of the current lane changing is recorded. Then, it is determined whether the curve needs to be optimized to determine the total lane changing time t2 of the optimized lane changing curve in the next work section.

[0091] The difference between the set speed and the actual speed of the road roller during lane changing in the pre-work section is calculated. If the difference is greater than 1 km / h, it indicates that the curve needs to be optimized, and the lane changing curve optimization will be performed and the optimized lane changing curve will be used in the first work section. After obtaining the total lane changing time t2 of the pre-work section, the time t1 of the straight rolling area in the first work section is obtained by T-t2. The optimal compaction speed v of the road roller is determined according to experience, the speed of the road roller is fixed as the optimal compaction speed v, and the length of the straight rolling area in the first work section is set as L=v·t1 / q. When working in the first work section, the total lane changing time t2 of the first work section is recorded, and the difference between the set speed and the actual speed of the road roller is calculated. If the difference is greater than 1 km / h, the lane changing curve optimization needs to be performed, and the lane changing in the second work section is performed according to the optimized lane changing curve of the first section. The total lane changing time t2 of the second work section is recorded, and the total working time t1 of the straight rolling area in the second work section is recalculated by T-t2. At this time, t2 is the total lane changing time of the first work section. In this way, the length of the straight rolling area in all work sections is obtained.

[0092] If the difference between the set speed and the actual speed of the road roller in the current work section is less than 1 km / h, it indicates that the lane changing is smooth, and the lane changing curve of the next work section does not need to be optimized, and the lane changing curve of the current work section is still used.

[0093] The parts not mentioned in the present application are applicable to the prior art.

Claims

1. A temperature-mass-driven path optimization method for the entire operation process of a road surface unmanned aerial vehicle (UAV) swarm, characterized in that, The method includes the following: The temperature data of asphalt mixture under different environmental conditions are obtained, and an intelligent prediction algorithm is used to establish a prediction model that can predict the temperature decay curve of asphalt mixture under different environmental conditions. The surface temperature and actual temperature of asphalt mixture radiated outward during compaction under different environmental conditions are obtained. Based on this, an intelligent prediction model is used to establish a real-time monitoring model for the actual temperature of asphalt mixture. This model can obtain the relationship between the surface temperature and actual temperature of asphalt mixture radiated outward during compaction under different environmental conditions, and enable real-time monitoring of the actual internal temperature of asphalt mixture during compaction. When the machine group is carrying out compaction operations, the work section is divided into straight rolling areas and lane-changing areas. During compaction in the straight rolling areas, the actual temperature of the asphalt at the compaction location is predicted and recorded in real time using a real-time asphalt mixture temperature monitoring model. Then, based on the current working environment, an asphalt mixture temperature decay curve prediction model is used to predict an asphalt mixture temperature decay curve that conforms to the site conditions. The optimal compaction time window T corresponding to the optimal compaction temperature range is determined on the decay curve. max The length of the next work segment is determined based on the optimal compaction time window. The total work time T of the machine group within any work segment ranges from 0.75T. max <T<0.9T max At this time T max The temperature decay curve of the asphalt mixture in the first working section is determined by the actual temperature data of the asphalt mixture in the previous working section. The temperature decay curve of the asphalt mixture in the first working section is generated by the actual temperature data of the asphalt mixture in the pre-working section. Under the premise that the speed V of the roller remains unchanged, the length of the working section is divided according to L=V(T-t2) / q. Where L is the length of the straight compaction area in the work section, i.e. the length of the work section; t2 is the total time spent changing lanes in the same work section; and q is the number of straight compaction lanes that one roller is responsible for in the work section. During actual operation of the machine group, compaction is carried out according to the divided work sections. The difference between the actual temperature of the asphalt mixture predicted by the real-time temperature monitoring model and the temperature value predicted on the temperature decay curve at that point is compared. A temperature difference threshold is set. If the difference is greater than the temperature difference threshold, the roller is accelerated to ensure that the roller completes the compaction operation within the optimal compaction time window.

2. The method according to claim 1, characterized in that, During compaction operations, the path planning for rolling and lane changing is optimized. The straight rolling area includes several straight rolling lanes parallel to the roadside. The number of straight rolling lanes is determined by the road width, the roller wheel width, and the overlap width of adjacent straight rolling lanes. The lane changing area includes several curved sections. The lane changing curves are selected as third-order Bézier curves. These curves ensure that the roller body is straightened and the articulated steering angle is zero after lane changing, and that the entire lane changing path is continuous and smooth, satisfying the kinematic and dynamic constraints of the roller. At the same time, straight rolling and curved lane changing are carried out alternately to ensure that the roller can compact all the asphalt mixture in the working section in a short time. Before compaction, a pre-compaction section is set up for pre-compaction. The optimal compaction speed of the roller is determined based on experience and fixed as the optimal compaction speed. A speed difference threshold is set. Compaction is carried out in the pre-compaction section, and the speed difference between the real-time speed and the optimal compaction speed during lane changing is recorded. At the same time, the total lane changing time t2 is recorded. If the speed difference is greater than the speed difference threshold, the lane changing curve of the next operation section needs to be optimized to obtain the optimized lane changing curve. In each work segment, the total working time t1 of the straight compaction area is determined by T-t2. At this time, t2 is the actual total lane change time of the previous work segment. Then, the length of the current work segment is determined according to L=v·t1 / q. The lane change curves of different compaction tracks in the same work segment are the same. The optimization t2 of each work segment changes and shows a trend of becoming shorter. Correspondingly, the length of the straight compaction area increases, thereby optimizing the length of the work segment.

3. The method according to claim 2, characterized in that, The third-order Bézier curve is formed by the starting point P0, the ending point P3, and two points P1 and P2 in the longitudinal direction of travel. The lane-changing curve optimization process is as follows: First, optimize the coordinates of P1 and P2 to minimize the difference between the maximum and minimum radii of curvature of the planned curve. This ensures that the lane-changing path is continuous and smooth throughout the entire lane-changing process, and also controls the maximum value of the relative turning angle between the front and rear of the roller within a certain range, thus ensuring the efficiency of the lane-changing. The optimization function for P1 and P2 is: J(P1,P2)=k max (t a )-k min (t b ),t a ,t b ∈(0,1), t a ,t b To obtain the maximum radius of curvature k of the Bézier curve max With minimum radius of curvature k min The value at time; Secondly, if, during lane changing, it is found that after optimizing control points P1 and P2, the speed difference between the real-time speed of the roller and the optimal compaction speed L of the roller is still greater than the speed difference threshold, it indicates that the lane changing area length is set too small. In this case, the starting point P0 of the lane changing will remain unchanged, and the position of the ending point P3 will be adjusted to increase the length of the lane changing area. The process of optimizing the coordinates of P1 and P2 and adjusting the position of the ending point P3 will be repeated until the speed difference is controlled within the speed difference threshold range. The length of the lane changing area will increase by 0.5m each time.

4. The method according to claim 1, characterized in that, The asphalt mixture temperature decay curve prediction model includes an intelligent prediction algorithm and a fitting module. The input of the intelligent prediction algorithm is ambient temperature, ambient humidity and wind speed, and the output is the asphalt mixture temperature for a future period of time. The intelligent prediction algorithm uses at least one of LSTM, Transformer, BiLSTM and GRU. The input of the fitting module is the historical asphalt mixture temperature before prediction and the asphalt mixture temperature after prediction, and the output is the decay curve.

5. The method according to claim 1, characterized in that, The intelligent prediction model takes ambient temperature, ambient humidity, actual wind speed, vehicle speed, and surface temperature of the asphalt mixture radiating outward as input, and outputs the actual temperature of the asphalt mixture. The intelligent prediction algorithm employs at least one of BP neural network, ANN neural network, and RNN neural network.

6. A temperature-mass-driven path optimization system for the entire process of unmanned aerial vehicle (UAV) swarm operations on roads, implementing the method described in any one of claims 1-5, comprising a plurality of road rollers, and a control module, a host computer, and a decision-making module for assisted automatic driving, characterized in that, The roller is equipped with a monocular camera to detect the road edges on both sides to prevent it from leaving the working area and causing danger; an angle sensor to acquire the relative turning angle of the vehicle body; a speed sensor to acquire the speed of the roller; a thermometer and hygrometer to collect ambient temperature and humidity; an infrared thermometer to collect the surface temperature of the asphalt mixture radiated outwards; a wind speed sensor to collect relative wind speed; and an RTK GNSS to collect the real-time location information of the roller. The host computer is used to view the real-time operation status of the machine group, including the visual display of the compaction of the machine group in the work area, the compaction parameters of each roller in the machine group, the real-time temperature display of the compacted material, and the path planning based on the optimal compaction temperature range. The decision module communicates wirelessly with the host computer and can acquire data from a monocular camera, angle sensor, speed sensor, thermometer and hygrometer, infrared thermometer, RTK GNSS and wind speed sensor. It is also loaded with a prediction model for the temperature decay curve of asphalt mixture and a real-time monitoring model for the actual temperature of asphalt mixture. The asphalt mixture temperature decay curve prediction model is used to predict the temperature decay curve of asphalt mixture under different environmental conditions. The real-time monitoring model for the actual temperature of asphalt mixture is used to obtain the relationship between the surface temperature radiated outward by the asphalt mixture and the actual temperature during compaction operations under different environmental conditions.

7. The system according to claim 6, characterized in that, The decision module also includes a lane-changing curve optimization algorithm, which is used to optimize the speed difference between the set speed and the actual speed of the road roller at the two middle control points and the end point on the third-order Bezier curve until the speed difference is controlled within the set speed difference threshold range. The length of the straight compaction zone for the next work section is determined based on the total lane change time of the previous work section.

Images