Unmanned sweeper edgewise path tracking control method and system

Abstract

The invention relates to the technical field of intelligent unmanned sweeping, in particular to an unmanned sweeping vehicle edge path tracking control method and system. Through cooperative work of a path planning and edge feature detection module, a real-time positioning and attitude estimation module, an edge tracking control module, an obstacle detection and avoidance module, a path correction and feedback module and an energy consumption optimization and endurance control module, precise tracking of the sweeper on an edge path in a complex environment is realized. Through multi-sensor data fusion, extended Kalman filtering and a self-adaptive path tracking algorithm, the system can adjust the driving state of the motor sweeper in real time, it is ensured that the motor sweeper is driven accurately along the edge, through a dynamic path planning algorithm and an energy consumption optimization model, the ability of the motor sweeper in the aspects of obstacle avoidance, path correction and endurance control is effectively improved, and the motor sweeper driving stability is improved. Therefore, the working efficiency and the endurance time are improved on the premise that the cleaning task requirement is met. The device is suitable for various complex sweeping environments, and efficient edge sweeping operation is achieved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent unmanned cleaning technology, and in particular to a method and system for controlling an unmanned cleaning vehicle's edge path tracking. Background Art

[0002] With the rapid development of intelligent unmanned vehicle technology, unmanned road sweepers, as an automated cleaning equipment, are widely used in municipal roads, industrial parks, residential areas, etc. Unmanned road sweepers can automatically drive accurately along the edge of the cleaning area through edge path tracking technology to ensure efficient and full coverage cleaning effect.

[0003] Most of the existing unmanned road sweeper path tracking technologies rely on single or local sensor data, such as GPS positioning, laser radar or visual sensor data. These technologies have obvious deficiencies in obstacle detection, path deviation correction and energy consumption optimization. In complex environments, a single sensor is susceptible to obstacle occlusion, signal interference and environmental changes, resulting in reduced path tracking accuracy and cleaning efficiency. In addition, the existing technology lacks efficient energy consumption management and dynamic adjustment mechanisms, and road sweepers are prone to operate in a high energy consumption state, resulting in short battery life and low efficiency. Summary of the invention

[0004] Based on the above objectives, the present invention provides a method and system for controlling an edge path tracking of an unmanned sweeper.

[0005] A method for controlling an unmanned road sweeper along a path, comprising the following steps:

[0006] S1, path planning and edge feature detection: By fusing multi-sensor data (such as ultrasonic sensors, lidar, cameras, etc.), the working area of ​​the unmanned sweeper is identified, and preliminary path planning is performed based on the edge features of the working area;

[0007] S2, real-time positioning and attitude estimation: adopt a positioning method based on the fusion of odometer and inertial measurement unit to obtain the real-time position and attitude information of the unmanned sweeper, and at the same time combine environmental data to correct the position deviation;

[0008] S3, edge tracking control: By designing an adaptive path tracking control algorithm, combined with the unmanned sweeper's dynamic model and the edge characteristics of the working area, the yaw angle and distance error are calculated in real time, and corresponding control instructions are generated, so that the unmanned sweeper can drive along the edge and accurately complete the cleaning task;

[0009] S4, obstacle detection and avoidance: When the unmanned sweeper performs edge path tracking, it uses ultrasonic sensors and lidar to detect obstacles on the cleaning path in real time. Combined with the dynamic path planning algorithm, it adjusts the path of the sweeper to avoid obstacles and returns to the edge path after avoiding obstacles, ensuring the continuity of the cleaning task;

[0010] S5, path correction and feedback: By analyzing the real-time position, path deviation and sensor data of the unmanned sweeper, a path tracking error model is constructed to correct the actual cleaning trajectory of the unmanned sweeper, and the correction result is fed back to the control system to adjust the driving state of the unmanned sweeper in real time to ensure that the sweeper always cleans efficiently along the predetermined edge;

[0011] S6, energy consumption optimization and endurance control: Based on the real-time operation data and path information of the unmanned sweeper, combined with the cleaning task requirements, an energy consumption optimization model is designed. While ensuring the path tracking accuracy, the operating speed and cleaning mode of the unmanned sweeper are dynamically adjusted to extend the endurance of the sweeper and improve its work efficiency.

[0012] Optionally, the S1 includes:

[0013] S11, multi-sensor data acquisition: The ultrasonic sensor, lidar and camera installed on the unmanned sweeper collect environmental data of the working area in real time. The ultrasonic sensor is used to measure the distance of close-range obstacles, the lidar is used to generate point cloud data, and the camera is used to obtain visual image information to identify edge features in the environment.

[0014] S12, sensor data synchronization and preprocessing, time synchronization and noise filtering of data collected by ultrasonic sensors, lidar and cameras;

[0015] S13, sensor data fusion, fuses the pre-processed data of each sensor to form a unified environment model. The fusion process is implemented through a weighted fusion algorithm, which is expressed as:

[0016] E fused =w1·E ultrasonic +w2·E lidar +w3·E camera ;

[0017] Among them, E fused is the fused environmental data, w1, w2, w3 are the weights of each sensor;

[0018] S14, edge feature extraction, applying the Canny edge detection algorithm to the fused environmental data to extract edge features and generate edge feature data in the working area of ​​the unmanned sweeper;

[0019] S15, preliminary path planning: Based on edge feature data, use A algorithm to perform path planning and generate the optimal path.

[0020] Optionally, S2 includes:

[0021] S21, odometer data collection: The wheel speed sensor and encoder of the unmanned sweeper are used to collect the travel distance and speed information in real time, and the relative displacement of the sweeper is calculated based on the wheel speed data to preliminarily estimate the position of the unmanned sweeper in the two-dimensional plane;

[0022] S22, inertial measurement unit data acquisition: the inertial measurement unit installed on the unmanned sweeper is used to obtain three-axis acceleration and angular velocity data in real time to calculate the posture change of the unmanned sweeper;

[0023] S23: Data fusion and position estimation, using extended Kalman filter to fuse odometer data and inertial measurement unit data to improve positioning accuracy;

[0024] S24, environmental data fusion: Combine the environmental data collected by ultrasonic sensors and lidar, analyze the positions of obstacles and edge features around the unmanned sweeper, fuse the environmental data into the positioning system, and correct the position and attitude deviations. For example, the lateral offset of the sweeper is corrected by the edge data of the lidar to ensure that the sweeper can travel along the predetermined edge.

[0025] S25, position and posture correction: The real-time position and posture of the unmanned sweeper are corrected based on the fused data to ensure that it maintains a stable driving state along the edge path in a complex environment. If a position or posture deviation occurs, the movement state of the sweeper will be automatically adjusted to correct the deviation.

[0026] Optionally, the S3 specifically includes:

[0027] S31, dynamic model establishment: according to the motion characteristics of the unmanned sweeper, establish its dynamic model;

[0028] S32, edge feature extraction: based on the edge feature data in the path planning, the expected position of the target path is calculated using the extracted edge information;

[0029] S33, Adaptive path tracking control algorithm design: Design control algorithm using PID controller to adjust steering angle and speed in real time;

[0030] S34, control command generation: Generate control commands for the unmanned sweeper according to the calculated steering angle and speed, and send the commands to the actuator through the control system to ensure that the sweeper can adjust the driving state in real time and achieve accurate edge tracking;

[0031] S35, path tracking feedback and optimization: During the driving process of the unmanned sweeper, the deviation between the actual driving trajectory of the unmanned sweeper and the target edge is monitored in real time, and the control parameters are dynamically adjusted according to the feedback information.

[0032] Optionally, the S4 includes:

[0033] S41, obstacle detection: The obstacles on the cleaning path are monitored in real time through ultrasonic sensors and lidar installed on the unmanned sweeper;

[0034] S42, obstacle feature analysis: after the obstacle is detected, analyze the specific features of the obstacle, including the position, size, and relative position to the path of the sweeper;

[0035] S43, dynamic path planning: Based on the obstacle characteristics and the current path of the unmanned sweeper, the Dijkstra algorithm is used to generate an obstacle avoidance path to ensure that the sweeper can bypass the obstacle and maintain safe driving;

[0036] S44, obstacle avoidance path execution: according to the optimal obstacle avoidance path calculated by the Dijkstra algorithm, a control instruction of the sweeper is generated, including adjusting the driving direction and speed to safely bypass obstacles. Through steering and speed control, the sweeper drives along the obstacle avoidance path to ensure the continuity of the cleaning task;

[0037] S45, path recovery after obstacle avoidance: After the unmanned sweeper completes obstacle avoidance, the relative position of the unmanned sweeper is detected and the path is corrected to ensure that the sweeper returns to the path along the edge to continue the cleaning task.

[0038] Optionally, the S5 includes:

[0039] S51, real-time position and path deviation analysis: using the sensor data of the unmanned sweeper to obtain the current real-time position and posture of the unmanned sweeper, and comparing the position information with the target point on the predetermined edge path, and calculating the current path deviation, including lateral deviation and yaw angle deviation;

[0040] S52, path tracking error model construction: based on the lateral deviation and yaw angle deviation of the sweeper, a path tracking error model is constructed to evaluate the degree of deviation of the sweeper from the predetermined path in real time.

[0041] Optionally, S5 further includes:

[0042] S53, path correction calculation: based on the deviation value calculated by the path tracking error model, the driving trajectory of the unmanned sweeper is corrected in real time;

[0043] S54, feedback adjustment mechanism: the path correction result is fed back to the control system, and the driving status of the sweeper is monitored in real time. According to the feedback information, the control system dynamically adjusts the operating parameters of the unmanned sweeper, including the steering angle and speed, to ensure that the sweeper can drive stably along the predetermined edge after the path correction. If a new path deviation is detected, it will automatically enter the path correction loop to further optimize the driving path of the unmanned sweeper.

[0044] Optionally, the S6 includes:

[0045] S61, real-time operation data collection: The sensors on the unmanned sweeper collect real-time operation data, including speed, driving path, cleaning mode and power consumption, to evaluate the current energy consumption status and compare it with the task requirements, providing a basis for energy consumption optimization;

[0046] S62, energy consumption assessment and demand analysis: Analyze the energy consumption demand of the current task according to the requirements of the cleaning task and the real-time path information. For example, if the cleaning area is dense or the edge path is complex, adjust the speed and cleaning intensity of the cleaning vehicle to avoid excessive energy consumption;

[0047] S63, energy consumption optimization model construction: based on the real-time operation data and task requirements of the sweeper, an energy consumption optimization model is established. The goal of the energy consumption optimization model is to minimize the energy consumption per unit area of ​​the sweeper.

[0048] Optionally, S6 further includes:

[0049] S64, dynamic adjustment of speed and cleaning mode: according to the calculation results of the energy consumption optimization model, the operating speed and cleaning mode of the unmanned sweeper are adjusted in real time;

[0050] S65, Energy consumption feedback and control: Real-time monitoring of energy consumption during the cleaning process, comparing the current energy consumption level with the predicted value of the energy consumption optimization model. If it is detected that the energy consumption deviates from the optimization target, the operating parameters of the sweeper are automatically adjusted according to the feedback, such as reducing the cleaning power or adjusting the driving speed, to ensure that the energy consumption is within a reasonable range;

[0051] S66, Adaptive adjustment mechanism: Based on energy consumption feedback, an adaptive energy consumption adjustment mechanism is constructed. According to historical energy consumption data and real-time feedback, the parameters of the energy consumption optimization model are continuously optimized and adjusted to make the energy consumption adjustment strategy of the sweeper adapt to different cleaning scenarios and task requirements.

[0052] An unmanned road sweeper path tracking control system, used to implement the above-mentioned unmanned road sweeper path tracking control method, includes the following modules:

[0053] Path planning and edge feature detection module: used to identify the working area of ​​the unmanned sweeper through multi-sensor data (including ultrasonic sensors, lidar and cameras), and perform path planning based on the edge features of the working area to ensure that the sweeper can travel along the edge path;

[0054] Real-time positioning and attitude estimation module: used to obtain the real-time position and attitude information of the unmanned sweeper by combining the odometer and inertial measurement unit, and correct the position deviation by combining the environmental data to ensure that the sweeper can drive stably along the edge in a complex environment;

[0055] Edge tracking control module: used to execute the adaptive path tracking control algorithm, combine the dynamic model of the unmanned sweeper and the edge characteristics of the working area, calculate the yaw angle and distance error in real time, and generate control instructions (such as steering angle and speed adjustment) to make the unmanned sweeper drive along the edge;

[0056] Obstacle detection and avoidance module: used to detect obstacles on the cleaning path in real time through ultrasonic sensors and lidar, and adjust the path of the sweeper to avoid obstacles in combination with a dynamic path planning algorithm. At the same time, after avoiding obstacles, the sweeper returns to the path along the edge to ensure the continuity of the cleaning task;

[0057] Path correction and feedback module: used to analyze the real-time position, path deviation and sensor data of the unmanned sweeper, build a path tracking error model, correct the actual cleaning trajectory, and feed back the correction results to the control system to ensure that the sweeper always cleans efficiently along the predetermined edge path;

[0058] Energy consumption optimization and endurance control module: used to design an energy consumption optimization model based on the real-time operation data and path information of the sweeper and the cleaning task requirements, dynamically adjust the operating speed and cleaning mode of the unmanned sweeper, extend the endurance time, and improve work efficiency.

[0059] Beneficial effects of the present invention:

[0060] The present invention realizes accurate tracking of the unmanned sweeper on the path along the edge through the coordinated work of the path planning and edge feature detection module, the real-time positioning and posture estimation module, and the edge tracking control module. The application of multi-sensor data fusion technology and extended Kalman filtering ensures real-time position correction in complex environments, and maintains the alignment of the sweeper with the target edge through the adaptive path tracking control algorithm, which significantly improves the path tracking accuracy and effectively reduces the path deviation that may occur during the cleaning process, thereby improving the cleaning coverage rate and ensuring that the unmanned sweeper can achieve efficient cleaning while driving along the edge.

[0061] The obstacle detection and avoidance module of the present invention can quickly identify obstacles on the cleaning path through real-time data from ultrasonic sensors and laser radars, and dynamically plan detour paths using the Dijkstra algorithm. After the avoidance is completed, the system automatically returns to the path along the edge to achieve seamless path tracking. The path correction and feedback module further ensures that the path recovery process of the sweeper after obstacle avoidance is accurate and stable through the construction and real-time correction of the error model, so that the cleaning task can be continuously and efficiently executed, and is suitable for complex and changeable cleaning environments.

[0062] In the present invention, the energy consumption optimization and endurance control module constructs an energy consumption optimization model based on real-time operation data and path information, and dynamically adjusts the speed and cleaning mode of the unmanned sweeper to reduce power consumption while meeting the requirements of the cleaning task. The system's adaptive energy consumption feedback mechanism can continuously optimize and adjust parameters according to actual energy consumption conditions to ensure that the sweeper can extend its endurance without affecting the cleaning effect. This design effectively improves the operating efficiency of the unmanned sweeper, enables it to adapt to a variety of work tasks, reduces the need for frequent charging or maintenance, and provides a guarantee for long-term and efficient cleaning. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0064] Figure 1 A schematic diagram of a method flow chart of an embodiment of the present invention;

[0065] Figure 2 Schematic diagram of a system flow of an embodiment of the present invention. DETAILED DESCRIPTION

[0066] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0067] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0068] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0069] like Figure 1 As shown, a method for controlling an unmanned sweeper along a path for edge tracking includes the following steps:

[0070] S1, path planning and edge feature detection: By fusing multi-sensor data (such as ultrasonic sensors, lidar, cameras, etc.), the working area of ​​the unmanned sweeper is identified, and preliminary path planning is performed based on the edge features of the working area to ensure that the sweeper can track the path along the edge;

[0071] S2, real-time positioning and attitude estimation: A positioning method based on the fusion of odometer and inertial measurement unit is used to obtain the real-time position and attitude information of the unmanned sweeper. At the same time, the position deviation is corrected in combination with environmental data to ensure that the unmanned sweeper can stably drive along the edge in a complex environment.

[0072] S3, edge tracking control: By designing an adaptive path tracking control algorithm, combined with the dynamic model of the unmanned sweeper and the edge characteristics of the working area, the yaw angle and distance error are calculated in real time, and corresponding control instructions (such as steering angle and speed adjustment) are generated, so that the unmanned sweeper can drive along the edge and accurately complete the cleaning task;

[0073] S4, obstacle detection and avoidance: When the unmanned sweeper performs edge path tracking, it uses ultrasonic sensors and lidar to detect obstacles on the cleaning path in real time. Combined with the dynamic path planning algorithm, it adjusts the path of the sweeper to avoid obstacles and returns to the edge path after avoiding obstacles, ensuring the continuity of the cleaning task;

[0074] S5, path correction and feedback: By analyzing the real-time position, path deviation and sensor data of the unmanned sweeper, a path tracking error model is constructed to correct the actual cleaning trajectory of the unmanned sweeper, and the correction result is fed back to the control system to adjust the driving state of the unmanned sweeper in real time to ensure that the sweeper always cleans efficiently along the predetermined edge;

[0075] S6, energy consumption optimization and endurance control: Based on the real-time operation data and path information of the unmanned sweeper, combined with the cleaning task requirements, an energy consumption optimization model is designed. While ensuring the path tracking accuracy, the operating speed and cleaning mode of the unmanned sweeper are dynamically adjusted to extend the endurance of the sweeper and improve its work efficiency.

[0076] S1 includes:

[0077] S11, multi-sensor data acquisition: The ultrasonic sensor, lidar and camera installed on the unmanned sweeper collect environmental data of the working area in real time. The ultrasonic sensor is used to measure the distance of close-range obstacles, the lidar is used to generate point cloud data, and the camera is used to obtain visual image information to identify edge features in the environment.

[0078] S12, sensor data synchronization and preprocessing, time synchronization and noise filtering of data collected by ultrasonic sensors, lidar and cameras to ensure data consistency and accuracy and remove irrelevant interference information;

[0079] S13, sensor data fusion, fuses the pre-processed data of each sensor to form a unified environment model. The fusion process is implemented through a weighted fusion algorithm, which is expressed as:

[0080] E fused =w1·E ultrasonic +w2·E lidar +w3·E camera ;

[0081] Among them, E fused is the fused environmental data, w1, w2, w3 are the weights of each sensor, which are used to balance the accuracy and importance of each data source;

[0082] S14, edge feature extraction, applies the Canny edge detection algorithm to the fused environmental data to extract edge features and generate edge feature data in the working area of ​​the unmanned sweeper, which is expressed as:

[0083] P edge ={(x i ,y i )|i=1,2,…,N};

[0084] Among them, P edgeis the detected edge point set, N is the number of detected edge points, x i ,y i Represents the coordinates of edge points;

[0085] S15, preliminary path planning: Based on edge feature data, use the A algorithm for path planning to generate the optimal path. The cost function of the A algorithm is expressed as:

[0086] f(n)=g(n)+h(n);

[0087] Among them, f(n) is the total cost of the current node n, g(n) is the actual cost from the starting point to the current node, h(n) is the estimated cost (heuristic function) from the current node to the target point, and the heuristic function h(n) is estimated using the Euclidean distance, expressed as:

[0088] Among them, (x goal ,y goal ) is the target point coordinate, (x n ,y n ) is the coordinate of the current node. By continuously calculating the value of f(n), an optimal path from the starting point to the target point is found, and the dynamic characteristics of the unmanned sweeper are considered to adjust the planned path;

[0089] Through multi-sensor data collection, preprocessing, fusion, edge feature extraction and path planning, the unmanned sweeper can identify edges in complex environments, generate the path planning required for cleaning tasks, and ensure the accuracy and stability of the sweeper's driving along the edge.

[0090] S2 includes:

[0091] S21, odometer data collection: The wheel speed sensor and encoder of the unmanned sweeper are used to collect the driving distance and speed information in real time. The relative displacement of the sweeper is calculated based on the wheel speed data, and the position of the unmanned sweeper in the two-dimensional plane is preliminarily estimated. The relative displacement data obtained is expressed as:

[0092] Δx=v·cos(θ)·Δt;

[0093] Δy=v·sin(θ)·Δt;

[0094] Where Δx and Δy are the displacements within the time interval Δt, v ​​is the velocity, and θ is the current direction angle;

[0095] S22, inertial measurement unit data acquisition: The inertial measurement unit installed on the unmanned sweeper is used to obtain three-axis acceleration and angular velocity data in real time to calculate the posture change of the unmanned sweeper. The angular velocity is used to update the posture angle, which is calculated as:

[0096] θ k+1=θ k +ω·Δt;

[0097] Among them, θ k+1 is the updated attitude angle, ω is the angular velocity, Δt is the time increment, θ k is the current attitude angle;

[0098] For acceleration data, update the velocity and position based on the acceleration:

[0099] The speed update formula is expressed as:

[0100] v k+1 =v k +a·Δt;

[0101] The position update formula is expressed as:

[0102]

[0103] Among them, v k is the current speed, a is the acceleration, s k is the current displacement;

[0104] S23: Data fusion and position estimation. Use the extended Kalman filter to fuse the odometer data and the inertial measurement unit data to improve positioning accuracy. The state estimation formula of the extended Kalman filter is:

[0105]

[0106] in, is the predicted state vector, K k is the Kalman gain, z k is the observed value, H k The extended Kalman filter adjusts the predicted position according to the sensor error during the real-time update process to obtain more accurate position information.

[0107] S24, environmental data fusion: Combine the environmental data collected by ultrasonic sensors and lidar, analyze the positions of obstacles and edge features around the unmanned sweeper, fuse the environmental data into the positioning system, and correct the position and attitude deviations. For example, the lateral offset of the sweeper is corrected by the edge data of the lidar to ensure that the sweeper can travel along the predetermined edge.

[0108] S25, position and posture correction: Based on the fused data, the real-time position and posture of the unmanned sweeper are corrected to ensure that it maintains a stable driving state along the edge path in a complex environment. If a position or posture deviation occurs, the movement state of the sweeper will be automatically adjusted to correct the deviation;

[0109] Through the fusion calculation of odometer, inertial measurement unit and environmental data, the unmanned sweeper can obtain accurate positioning and attitude estimation in real time in complex environments. The extended Kalman filter and multi-source data fusion improve the positioning stability and accuracy, allowing the sweeper to travel stably along the predetermined edge path, improving the continuity and reliability of the cleaning operation.

[0110] S3 specifically includes:

[0111] S31, dynamic model establishment: according to the motion characteristics of the unmanned sweeper, its dynamic model is established, the state variables are set as x (lateral displacement), y (longitudinal displacement), θ (attitude angle) and c (speed), and the control input is defined as the steering angle δ and the forward speed v. The motion equation of the unmanned sweeper is expressed as:

[0112]

[0113] Wherein, L is the wheelbase of the sweeper;

[0114] S32, edge feature extraction: Based on the edge feature data in the path planning, the expected position of the target path is calculated using the extracted edge information, and the yaw angle error e is determined by comparing the current position of the unmanned sweeper with the target edge position. θ and distance error e d , calculated as:

[0115] e θ =θ target -θ current ;

[0116] e d =d target -d current ;

[0117] Among them, θ target is the direction angle of the target edge, d target and d current are the expected distance and current distance of the target edge respectively;

[0118] S33, adaptive path tracking control algorithm design: The control algorithm is designed using a PID controller to adjust the steering angle δ and speed v in real time. The control input is expressed as:

[0119]

[0120] v=v desired -K v ·e d ;

[0121] Among them, K p , K i , K dare the proportional, integral and derivative gains of the PID controller, v desired is the expected forward speed, K v is the gain of the distance error;

[0122] S34, control command generation: Generate control commands for the unmanned sweeper according to the calculated steering angle and speed, and send the commands to the actuator through the control system to ensure that the sweeper can adjust the driving state in real time and achieve accurate edge tracking;

[0123] S35, path tracking feedback and optimization: During the driving process of the unmanned sweeper, the deviation between the actual driving trajectory of the unmanned sweeper and the target edge is monitored in real time, and the control parameters are dynamically adjusted according to the feedback information. If the tracking error is detected to increase, the PID controller parameters are optimized in time to improve the tracking accuracy and stability;

[0124] Through the combination of dynamic model, edge feature extraction and adaptive path tracking control algorithm, the unmanned sweeper can calculate the yaw angle and distance error in real time, generate corresponding control instructions, ensure that the sweeper can stably drive along the edge and effectively complete the cleaning task. This method improves the tracking accuracy and adaptability of the sweeper in complex environments.

[0125] S4 includes:

[0126] S41, Obstacle Detection: Obstacles on the cleaning path are monitored in real time by ultrasonic sensors and lidar installed on the unmanned sweeper. Ultrasonic sensors are used to detect the position and size of obstacles at close range, and lidar is used to generate two-dimensional point cloud data around the sweeper to identify the specific shape and position of obstacles.

[0127] S42, obstacle feature analysis: After the obstacle is detected, the specific features of the obstacle are analyzed, including the position, size and relative position to the path of the sweeper. The characteristic data of the obstacle is expressed as:

[0128] P obstacle ={(x i ,y i ,z i )|i=1,2,…,N};

[0129] Among them, (x i ,y i ,z i ) is the coordinate of the obstacle in the point cloud, and N is the number of points that constitute the obstacle;

[0130] S43, dynamic path planning: Based on the obstacle characteristics and the current path of the unmanned sweeper, the Dijkstra algorithm is used to generate an obstacle avoidance path to ensure that the sweeper can bypass the obstacle and maintain safe driving. The Dijkstra algorithm gradually selects the path with the lowest cost based on the actual cost from the starting point to each node, so that the sweeper can find an optimal path from the current location to the target location by bypassing the obstacle. The path cost is calculated as:

[0131]

[0132] Among them, f(n) is the total cost from the starting point to node n, w i The path cost of the street sweeper from one node to the next node (such as distance, turning cost, etc.);

[0133] S44, obstacle avoidance path execution: according to the optimal obstacle avoidance path calculated by the Dijkstra algorithm, a control instruction of the sweeper is generated, including adjusting the driving direction and speed to safely bypass obstacles. Through steering and speed control, the sweeper drives along the obstacle avoidance path to ensure the continuity of the cleaning task. After the obstacle avoidance is completed, the system will automatically adjust the direction of the sweeper to return to the edge path;

[0134] S45, path recovery after obstacle avoidance: After the unmanned sweeper completes obstacle avoidance, the relative position of the unmanned sweeper is detected and the path is corrected to ensure that the sweeper returns to the path along the edge to continue the cleaning task. The system fine-tunes the driving state of the sweeper according to the real-time position information to ensure the accuracy of path tracking and the continuity of the task;

[0135] Through real-time obstacle detection achieved by ultrasound and lidar, as well as dynamic path planning and path recovery based on the Dijkstra algorithm, the unmanned sweeper can effectively bypass obstacles and automatically return to the edge path after avoiding obstacles, ensuring the stability and continuity of the cleaning task and improving the sweeper's adaptability in complex environments.

[0136] S5 includes:

[0137] S51, real-time position and path deviation analysis: using the sensor data of the unmanned sweeper (such as GPS, inertial measurement unit, odometer) to obtain the current real-time position and posture of the unmanned sweeper, and compare the position information with the target point on the predetermined edge path, and calculate the current path deviation, including lateral deviation and yaw angle deviation;

[0138] S52, path tracking error model construction: Based on the lateral deviation and yaw angle deviation of the sweeper, a path tracking error model is constructed to evaluate the degree of deviation of the sweeper from the predetermined path in real time. The path tracking error model formula is expressed as:

[0139] Epath =f(e d ,e θ )=K m ·e d +K θ ·e θ ;

[0140] Among them, E path is the path tracking error, K m and K θ are the coefficients of the error model. Adjusting these coefficients can optimize the path tracking effect of the sweeper. This model can quantify the degree of deviation of the sweeper to facilitate subsequent path correction.

[0141] By analyzing the real-time position and path deviation of the sweeper, a path tracking error model is established to provide real-time deviation data for the unmanned sweeper. This helps to accurately detect and quantify path deviations, provide data support for real-time adjustment of the sweeper's driving status, and ensure cleaning accuracy.

[0142] The S5 also includes:

[0143] S53, path correction calculation: based on the deviation value calculated by the path tracking error model, the driving trajectory of the unmanned sweeper is corrected in real time, and the path correction is performed using a PID controller, and the path deviation is corrected by adjusting the steering angle and speed;

[0144] S54, feedback adjustment mechanism: Feedback the path correction result to the control system, monitor the driving status of the sweeper in real time, and dynamically adjust the operating parameters of the unmanned sweeper, including the steering angle and speed, according to the feedback information, to ensure that the sweeper can stably drive along the predetermined edge after the path correction. If a new path deviation is detected, it will automatically enter the path correction loop to further optimize the driving path of the unmanned sweeper;

[0145] Through the path correction calculation and feedback mechanism, the unmanned sweeper can make real-time corrections when path deviations are detected, and feed back the correction results to the control system to ensure that the sweeper always travels along the predetermined path and achieves efficient and continuous cleaning operations. This mechanism improves cleaning accuracy and path tracking stability.

[0146] S6 includes:

[0147] S61, real-time operation data collection: The sensors on the unmanned sweeper collect real-time operation data, including speed, driving path, cleaning mode and power consumption, to evaluate the current energy consumption status and compare it with the task requirements, providing a basis for energy consumption optimization;

[0148] S62, Energy consumption assessment and demand analysis: Analyze the energy consumption requirements of the current task according to the requirements of the cleaning task and the real-time path information. For example, if the cleaning area is dense or the edge path is complex, adjust the speed and cleaning intensity of the sweeper to avoid excessive energy consumption. This process combines the path tracking accuracy requirements with the cleaning task requirements to ensure path coverage and work efficiency.

[0149] S63, energy consumption optimization model construction: Based on the real-time operation data and task requirements of the sweeper, an energy consumption optimization model is established. The goal of the energy consumption optimization model is to minimize the energy consumption per unit area of ​​the sweeper, which is expressed as:

[0150]

[0151] Among them, E opt is the optimized energy consumption per unit area, P i is the power consumption of the road sweeper in the i-th time period, t i is the duration of the time period, A is the cleaned area, and the model dynamically adjusts parameters according to the cleaning task and path complexity to improve energy efficiency;

[0152] By collecting operating data in real time and building energy consumption optimization models, unmanned sweepers can optimize energy consumption per unit area while meeting the requirements of cleaning tasks, ensuring path tracking accuracy while improving work efficiency and extending battery life.

[0153] The S6 also includes:

[0154] S64, dynamic adjustment of speed and cleaning mode: According to the calculation results of the energy consumption optimization model, the operating speed and cleaning mode of the unmanned sweeper are adjusted in real time. If the path tracking accuracy requirement is high, the speed is reduced to ensure the path tracking quality; if the power is insufficient and the task priority is low, the cleaning intensity is reduced to extend the endurance time, thereby achieving energy consumption balance;

[0155] S65, Energy consumption feedback and control: Real-time monitoring of energy consumption during the cleaning process, comparing the current energy consumption level with the predicted value of the energy consumption optimization model. If it is detected that the energy consumption deviates from the optimization target, the operating parameters of the sweeper are automatically adjusted according to the feedback, such as reducing the cleaning power or adjusting the driving speed, to ensure that the energy consumption is within a reasonable range;

[0156] S66, Adaptive adjustment mechanism: Based on energy consumption feedback, an adaptive energy consumption adjustment mechanism is constructed. According to historical energy consumption data and real-time feedback, the parameters of the energy consumption optimization model are continuously optimized and adjusted, so that the energy consumption adjustment strategy of the sweeper can adapt to different cleaning scenarios and task requirements, ensuring cleaning efficiency while improving energy efficiency;

[0157] Through dynamic adjustment of speed and cleaning mode, energy consumption feedback and adaptive mechanism, the unmanned sweeper can achieve real-time energy consumption management, effectively extend the battery life, ensure the sweeper can achieve efficient cleaning under different task requirements, and improve overall work efficiency and power utilization.

[0158] like Figure 2 As shown, an unmanned sweeper along the edge path tracking control system is used to implement the above-mentioned unmanned sweeper along the edge path tracking control method, including the following modules:

[0159] Path planning and edge feature detection module: used to identify the working area of ​​the unmanned sweeper through multi-sensor data (including ultrasonic sensors, lidar and cameras), and perform path planning based on the edge features of the working area to ensure that the sweeper can travel along the edge path;

[0160] Real-time positioning and attitude estimation module: used to obtain the real-time position and attitude information of the unmanned sweeper by combining the odometer and inertial measurement unit, and correct the position deviation by combining the environmental data to ensure that the sweeper can drive stably along the edge in a complex environment;

[0161] Edge tracking control module: used to execute the adaptive path tracking control algorithm, combine the dynamic model of the unmanned sweeper and the edge characteristics of the working area, calculate the yaw angle and distance error in real time, and generate control instructions (such as steering angle and speed adjustment) to make the unmanned sweeper drive along the edge;

[0162] Obstacle detection and avoidance module: used to detect obstacles on the cleaning path in real time through ultrasonic sensors and lidar, and adjust the path of the sweeper to avoid obstacles in combination with a dynamic path planning algorithm. At the same time, after avoiding obstacles, the sweeper returns to the path along the edge to ensure the continuity of the cleaning task;

[0163] Path correction and feedback module: used to analyze the real-time position, path deviation and sensor data of the unmanned sweeper, build a path tracking error model, correct the actual cleaning trajectory, and feed back the correction results to the control system to ensure that the sweeper always cleans efficiently along the predetermined edge path;

[0164] Energy consumption optimization and endurance control module: used to design an energy consumption optimization model based on the real-time operation data and path information of the sweeper and the cleaning task requirements, dynamically adjust the operating speed and cleaning mode of the unmanned sweeper, extend the endurance time, and improve work efficiency.

[0165] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0166] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for controlling an unmanned road sweeper's path tracking along an edge, characterized in that: The following steps are involved: S1, path planning and edge feature detection: by fusing multi-sensor data, the working area of ​​the unmanned sweeper is identified, and preliminary path planning is performed based on the edge features of the working area; S2, real-time positioning and attitude estimation: adopt a positioning method based on the fusion of odometer and inertial measurement unit to obtain the real-time position and attitude information of the unmanned sweeper, and at the same time combine environmental data to correct the position deviation; S3, edge tracking control: By designing an adaptive path tracking control algorithm, combined with the dynamic model of the unmanned sweeper and the edge characteristics of the working area, the yaw angle and distance error are calculated in real time, and corresponding control instructions are generated to enable the unmanned sweeper to drive along the edge and complete the cleaning task; S4, obstacle detection and avoidance: When the unmanned sweeper performs edge path tracking, it uses ultrasonic sensors and lidar to detect obstacles on the cleaning path in real time, and combines dynamic path planning algorithms to adjust the path of the sweeper to avoid obstacles and return to the edge path after avoiding obstacles; S5, path correction and feedback: By analyzing the real-time position, path deviation and sensor data of the unmanned sweeper, a path tracking error model is constructed to correct the actual cleaning trajectory of the unmanned sweeper, and the correction result is fed back to the control system to adjust the driving state of the unmanned sweeper in real time; S6, energy consumption optimization and endurance control: Based on the real-time operation data and path information of the unmanned sweeper, combined with the cleaning task requirements, an energy consumption optimization model is designed. While ensuring the path tracking accuracy, the operating speed and cleaning mode of the unmanned sweeper are dynamically adjusted to extend the endurance of the sweeper and improve its work efficiency.

2. The method for controlling the path tracking of an unmanned road sweeper along the edge according to claim 1, characterized in that: The S1 includes: S11, multi-sensor data acquisition: The ultrasonic sensor, lidar and camera installed on the unmanned sweeper collect environmental data of the working area in real time. The ultrasonic sensor is used to measure the distance of close-range obstacles, the lidar is used to generate point cloud data, and the camera is used to obtain visual image information to identify edge features in the environment. S12, sensor data synchronization and preprocessing, time synchronization and noise filtering of data collected by ultrasonic sensors, lidar and cameras; S13, sensor data fusion, fuses the pre-processed data of each sensor to form a unified environment model, which is expressed as: HAVE BEEN fused =w1·E ultrasonic +w2·E lidar +w3·E camera ; Among them, E fused is the fused environmental data, w1, w2, w3 are the weights of each sensor; S14, edge feature extraction, applying the Canny edge detection algorithm to the fused environmental data to extract edge features and generate edge feature data in the working area of ​​the unmanned sweeper; S15, preliminary path planning: Based on edge feature data, use A algorithm to perform path planning and generate the optimal path.

3. The method for controlling the path tracking of an unmanned sweeper along the edge according to claim 2, characterized in that: The S2 includes: S21, odometer data collection: The wheel speed sensor and encoder of the unmanned sweeper are used to collect the travel distance and speed information in real time, and the relative displacement of the sweeper is calculated based on the wheel speed data to preliminarily estimate the position of the unmanned sweeper in the two-dimensional plane; S22, inertial measurement unit data acquisition: the inertial measurement unit installed on the unmanned sweeper is used to obtain three-axis acceleration and angular velocity data in real time to calculate the posture change of the unmanned sweeper; S23: Data fusion and position estimation, using extended Kalman filter to fuse odometer data and inertial measurement unit data to improve positioning accuracy; S24, environmental data fusion: Combine the environmental data collected by ultrasonic sensors and lidar, analyze the positions of obstacles and edge features around the unmanned sweeper, fuse the environmental data into the positioning system, and correct the position and attitude deviations; S25, position and posture correction: The real-time position and posture of the unmanned sweeper are corrected based on the fused data. If a position or posture deviation occurs, the movement state of the sweeper will be automatically adjusted to correct the deviation.

4. The method for controlling the path tracking of an unmanned sweeper along the edge according to claim 3, characterized in that: The S3 specifically includes: S31, dynamic model establishment: according to the motion characteristics of the unmanned sweeper, establish its dynamic model; S32, edge feature extraction: based on the edge feature data in the path planning, the expected position of the target path is calculated using the extracted edge information; S33, Adaptive path tracking control algorithm design: Design control algorithm using PID controller to adjust steering angle and speed in real time; S34, generating control instructions: generating control instructions for the unmanned sweeper according to the calculated steering angle and speed, and sending the instructions to the actuator through the control system; S35, path tracking feedback and optimization: During the driving process of the unmanned sweeper, the deviation between the actual driving trajectory of the unmanned sweeper and the target edge is monitored in real time, and the control parameters are dynamically adjusted according to the feedback information.

5. The method for controlling the path tracking of an unmanned road sweeper along the edge according to claim 4, characterized in that: The S4 includes: S41, obstacle detection: The obstacles on the cleaning path are monitored in real time through ultrasonic sensors and lidar installed on the unmanned sweeper; S42, obstacle feature analysis: after the obstacle is detected, analyze the specific features of the obstacle, including the position, size, and relative position to the path of the sweeper; S43, dynamic path planning: Based on the obstacle characteristics and the current path of the unmanned sweeper, the Dijkstra algorithm is used to generate an obstacle avoidance path to ensure that the sweeper can bypass the obstacle and maintain safe driving; S44, obstacle avoidance path execution: generating control instructions for the sweeper according to the optimal obstacle avoidance path calculated by the Dijkstra algorithm, including adjusting the driving direction and speed to safely avoid obstacles; S45, path recovery after obstacle avoidance: After the unmanned sweeper completes obstacle avoidance, the relative position of the unmanned sweeper is detected and the path is corrected.

6. The method for controlling the path tracking of an unmanned sweeper along the edge according to claim 5, characterized in that: The S5 includes: S51, real-time position and path deviation analysis: using the sensor data of the unmanned sweeper to obtain the current real-time position and posture of the unmanned sweeper, and comparing the position information with the target point on the predetermined edge path, and calculating the current path deviation, including lateral deviation and yaw angle deviation; S52, path tracking error model construction: based on the lateral deviation and yaw angle deviation of the sweeper, a path tracking error model is constructed to evaluate the degree of deviation of the sweeper from the predetermined path in real time.

7. The method for controlling the path tracking of an unmanned road sweeper along the edge according to claim 6, characterized in that: The S5 further includes: S53, path correction calculation: based on the deviation value calculated by the path tracking error model, the driving trajectory of the unmanned sweeper is corrected in real time; S54, feedback adjustment mechanism: the path correction result is fed back to the control system, the driving status of the sweeper is monitored in real time, and according to the feedback information, the control system dynamically adjusts the operating parameters of the unmanned sweeper, including the steering angle and speed. If a new path deviation is detected, it will automatically enter the path correction loop to optimize the driving path of the unmanned sweeper.

8. The method and system for controlling the path tracking along the edge of an unmanned sweeper according to claim 1, characterized in that: The S6 includes: S61, real-time operation data collection: collect real-time operation data through sensors on the unmanned sweeper, including speed, driving path, cleaning mode and power consumption, to evaluate the current energy consumption status; S62, energy consumption assessment and demand analysis: analyzing the energy consumption demand of the current task according to the requirements of the cleaning task and the real-time path information; S63, energy consumption optimization model construction: based on the real-time operation data and task requirements of the sweeper, an energy consumption optimization model is established. The goal of the energy consumption optimization model is to minimize the energy consumption per unit area of ​​the sweeper.

9. The method for controlling the path tracking of an unmanned road sweeper along the edge according to claim 8, characterized in that: The S6 further includes: S64, dynamic adjustment of speed and cleaning mode: according to the calculation results of the energy consumption optimization model, the operating speed and cleaning mode of the unmanned sweeper are adjusted in real time; S65, Energy consumption feedback and control: Real-time monitoring of energy consumption during the cleaning process, comparing the current energy consumption level with the predicted value of the energy consumption optimization model, and automatically adjusting the operating parameters of the sweeper based on the feedback if it is detected that the energy consumption deviates from the optimization target; S66, Adaptive adjustment mechanism: Based on energy consumption feedback, an adaptive energy consumption adjustment mechanism is constructed to continuously optimize and adjust the parameters of the energy consumption optimization model based on historical energy consumption data and real-time feedback.

10. A control system for tracking the path along the edge of an unmanned road sweeper, used to implement a method for tracking the path along the edge of an unmanned road sweeper as claimed in any one of claims 1 to 9, characterized in that: Includes the following modules: Path planning and edge feature detection module: used to identify the working area of ​​the unmanned sweeper through multi-sensor data and perform path planning based on the edge features of the working area; Real-time positioning and attitude estimation module: used to obtain the real-time position and attitude information of the unmanned sweeper by combining the odometer and inertial measurement unit, and correct the position deviation by combining the environmental data; Edge tracking control module: used to execute the adaptive path tracking control algorithm, combine the dynamic model of the unmanned sweeper and the edge characteristics of the working area, calculate the yaw angle and distance error in real time, and generate control instructions to make the unmanned sweeper drive along the edge; Obstacle detection and avoidance module: used to detect obstacles on the cleaning path in real time through ultrasonic sensors and lidar, and adjust the path of the sweeper to avoid obstacles in combination with dynamic path planning algorithms, and restore to the path along the edge after avoiding obstacles; Path correction and feedback module: used to analyze the real-time position, path deviation and sensor data of the unmanned sweeper, build a path tracking error model, correct the actual cleaning trajectory, and feed back the correction results to the control system; Energy consumption optimization and endurance control module: used to design an energy consumption optimization model based on the real-time operation data and path information of the sweeper and the cleaning task requirements, dynamically adjust the operating speed and cleaning mode of the unmanned sweeper, extend the endurance time, and improve work efficiency.

Images