Intelligent obstacle avoidance method and control system for unmanned aerial vehicle patrol along traffic line

Abstract

The invention provides an intelligent obstacle avoidance method for unmanned aerial vehicle patrol along a traffic line and a control system, and belongs to the technical field of unmanned aerial vehicle intelligent patrol. According to the method, electronic fence data are generated by defining a flight corridor and a boundary thereof, and the patrol unmanned aerial vehicle collects airborne sensor data and fuses the airborne sensor data with the electronic fence data, positioning data and external environment data to construct an environment cognition model. And based on the model, adopting a hybrid decision algorithm to synchronously process a preset flight rule and real-time sensed obstacle information, generating and executing a flight control instruction, and updating the environment cognition model in real time based on sensing feedback. The system comprises a patrol unmanned aerial vehicle, a ground control center and a distributed autonomous cabin station. According to the intelligent obstacle avoidance method and control system for unmanned aerial vehicle patrol along the traffic line, the obstacle avoidance capability and patrol efficiency of the unmanned aerial vehicle in a complex environment can be effectively improved, the flight safety is ensured, and the intelligent obstacle avoidance method and control system are suitable for efficient patrol tasks along the traffic line.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of unmanned aerial vehicle intelligent patrol, in particular to an intelligent obstacle avoidance method and control system for unmanned aerial vehicle patrol along a traffic route. BACKGROUND

[0002] With the continuous development of transportation infrastructure, the patrol work of traffic routes becomes more and more important. The traditional patrol method mainly relies on manual inspection, which is not only low in efficiency and high in cost, but also difficult to implement in some complex terrain or adverse weather conditions. In recent years, the rapid development of unmanned aerial vehicle technology has provided a new solution for traffic route patrol. Unmanned aerial vehicles have high flexibility, wide coverage, low cost and other advantages, which can effectively improve the patrol efficiency and quality.

[0003] However, unmanned aerial vehicles face many challenges in the process of traffic route patrol, the most important of which is obstacle avoidance. The environment along the traffic route is complex, and there are various static and dynamic obstacles such as trees, buildings, vehicles, pedestrians, etc. Unmanned aerial vehicles need to perceive these obstacles in real time and perform effective obstacle avoidance during flight to ensure flight safety and the smooth completion of patrol tasks. In addition, unmanned aerial vehicles also need to comply with the pre-set flight rules, such as flying within the designated flight corridor and avoiding entering the no-fly area.

[0004] Existing unmanned aerial vehicle obstacle avoidance technologies mainly rely on single sensors or simple obstacle avoidance algorithms, which have limitations in complex environments. For example, the obstacle avoidance method based on visual sensors is not effective in poor lighting conditions or low visibility; the obstacle avoidance method based on laser radar has high precision, but the cost is high and it is easily disturbed in some cases. In addition, most of the existing obstacle avoidance algorithms can only deal with static obstacles, and the obstacle avoidance ability for dynamic obstacles is weak.

[0005] Therefore, an intelligent obstacle avoidance method and control system that can integrate multiple sensor data, perceive complex environments in real time and effectively avoid obstacles is needed to meet the needs of unmanned aerial vehicle patrol along the traffic route. SUMMARY

[0006] The purpose of the present application is to provide an intelligent obstacle avoidance method and control system for unmanned aerial vehicle patrol along a traffic route, which can effectively improve the obstacle avoidance ability and patrol efficiency of unmanned aerial vehicles in complex environments, ensure flight safety, and be suitable for efficient patrol tasks along the traffic route.

[0007] To achieve the above purpose, the present application provides an intelligent obstacle avoidance method for unmanned aerial vehicle patrol along a traffic route, comprising the following steps: Step S1, defining a flight corridor and its boundary for the target traffic route, and generating electronic fence data; Step S2: The patrol drone collects data from its onboard sensors and integrates it with data from the electronic fence, location data, and external environment data to build an environmental cognition model. Step S3: Based on the environmental cognition model, a hybrid decision-making algorithm is used to simultaneously process the preset flight rules and the real-time perceived obstacle information to generate flight control commands; Step S4: Execute flight control commands and update the environmental cognition model in real time based on perception feedback.

[0008] Preferably, in step S1, the flight corridor and its boundaries are defined for the target traffic route, and electronic fence data is generated, including: The flight corridor is located within 200 meters of the roadbed extending outwards from the transportation route. Using the centerline of the traffic route as a reference, extend 100 meters to one side of the patrol area as the baseline. ; From the baseline Offset 90 meters away from the traffic line to generate the outer boundary line of the corridor. ; From the baseline Offset 90 meters towards the traffic line to generate the inner boundary line of the corridor. ; And the inner boundary line The closest distance to the transportation route is 10 meters; This creates a flight corridor with a width of 180 meters; baseline The function expression is constructed based on the survey data of the traffic routes: ; in, Represents the slope of a straight line. Represents the horizontal axis coordinate. Represents the y-intercept of the line. Indicates control points, Indicates the total number of control points. Indicates the first One sampling point, Describes the cubic B-spline basis functions. Indicates parameter variables; The geometric information of the flight corridor is equivalent to electronic fence data, including baselines. Function expression, outer boundary line and inner boundary line Location parameters and boundary tolerances .

[0009] Preferably, in step S2, the airborne sensor data includes: image sequences acquired by a vision sensor. point cloud data collected by a laser radar radar point trail collected by a millimeter wave radar and body angular velocity collected by an inertial measurement unit and acceleration ; The positioning data includes: unmanned aerial vehicle coordinates , altitude , pose information , wherein represents the latitude, represents the longitude, , y , z respectively represent three-dimensional space coordinates, represents the roll angle, represents the pitch angle, represents the yaw angle; The external environment data includes: monitoring data uploaded by fixed perception nodes , wind speed vector and precipitation data , the monitoring data includes real-time video frames taken by a line camera, heat source information detected by an infrared sensor, abnormal vibration signals collected by a vibration sensor, and line deformation data returned by a fiber strain sensor.

[0010] Preferably, in step S2, the specific process of constructing the environment cognition model is: Through a multi-source data fusion filter, the airborne sensor data, the positioning data and the external environment data are time and space synchronized and the coordinate systems are unified; The fused perception data is clustered and features are extracted to identify a static obstacle set and a dynamic obstacle set , and the specific process is: Clustering processing: using a density clustering algorithm DBSCAN to cluster the three-dimensional point cloud data in the geodetic coordinate system, setting a neighborhood radius =0.5 meters and a minimum number of points MinPts=5, and aggregating spatially adjacent points into a candidate obstacle cluster; Feature extraction: calculating the volume , surface area , centroid coordinates and average speed of each obstacle cluster; Dynamic judgment: when the average speed of the obstacle cluster is greater than 0.3 meters / second and the speed change rate is less than 5% in the last three sampling periods, it is determined to be a dynamic obstacle ; otherwise, it is determined to be a static obstacle ; for Every obstacle in By combining its historical trajectory with the body motion parameters of the inertial measurement unit, its velocity vector is estimated. And predict its future Trajectory over time ; Ultimately, the environmental cognition model It is expressed as a tuple containing the following elements: .

[0011] Preferably, in step S3, based on the environmental cognition model, a hybrid decision-making algorithm is used to simultaneously process preset flight rules and real-time perceived obstacle information to generate flight control commands, including the following steps: Step S31, Current position of the computer body To the nearest corridor boundary Euclidean distance and define the rules to follow the cost function. : ; in, , Both represent scaling factors; Step S32, Environmental Cognition Model For each obstacle in the sequence, calculate its collision risk with the machine. And the total obstacle avoidance cost is obtained by combining the results. : ; in, Indicates the body and the first The current distance to each obstacle This indicates a risk factor set based on obstacle type and relative speed. Indicates a positive value; Step S23: The problem of generating flight control commands is transformed into a multi-objective optimization problem, the cost function of which is... for: ; in, This indicates the cost of measuring flight comfort. The weight representing the cost of rule compliance. The weights representing the cost of obstacle avoidance. The weight representing the cost of flight comfort; By solving online using gradient descent or model predictive control framework, we can obtain... The optimal control instruction sequence is minimized, the first instruction is taken as the flight control instruction at the current time, and when it is detected that the wind force reaches level 7 and above, an automatic landing instruction or an instruction that only allows forward flight is generated, and flight towards the direction close to the traffic line is prohibited.

[0012] Preferably, in step S3, the weights of the rule compliance cost and the obstacle avoidance cost are dynamically adjusted based on the environmental risk factor: ; ; wherein, represents the reference weight of the rule compliance cost, represents the reference weight of the obstacle avoidance cost, , both represent adjustment coefficients, represents the environmental risk factor; The environmental risk factor is calculated as follows: ; wherein, , represents a weighting coefficient.

[0013] Preferably, when solving the cost function, the trajectory is taken as a constraint condition in the optimization framework, and the specific process is as follows: A prediction time domain is set, for each dynamic obstacle , represents a time variable, represents the current time; The candidate trajectory point set of the unmanned aerial vehicle in the prediction time domain is defined as , represents the candidate position of the unmanned aerial vehicle at ; Collision constraints are established: for all and , it is required that the Euclidean distance between and ≥ , represents a preset safety distance; Corridor constraints are established: for all , it is required that is located between and , and the distance to is not less than 0; The collision constraint and the corridor constraint are embedded in the optimization solving process of the multi-objective cost function, the constraint condition is converted into a cost item through the Lagrange multiplier method, or a penalty is applied to the candidate solution that violates the constraint in the gradient descent iteration, so that the generated future instruction sequence meets the safety and rule requirements in the entire prediction time domain.

[0014] Preferably, in step S4, the environment cognition model is updated in real time based on the perception feedback, including: The new observation data is matched with the existing obstacles through a data association algorithm, and the state estimation of the obstacles is updated using Bayesian filtering; After refreshing the environment cognition model, the cost function is recalculated and the new control instruction is solved to realize closed-loop decision updating.

[0015] The application also provides an intelligent patrol control system for implementing the above method, comprising: The patrol unmanned aerial vehicle is equipped with a sensor unit, a computing unit, a positioning unit and a communication unit. The sensor unit is used for collecting airborne sensor data. The positioning unit is used for obtaining the geodetic coordinates, altitude and pose information of the unmanned aerial vehicle. The communication unit is used for data interaction with the ground control center and the distributed autonomous cabin station. The computing unit is used for running a hybrid decision algorithm to generate flight control instructions in real time according to the environment cognition model, and when wind force reaches 7 or above, the unmanned aerial vehicle is controlled to automatically land or only allowed to fly forward, and prohibited to fly towards the direction close to the traffic line. The ground control center is used for configuring and issuing electronic fence data and task instructions. The distributed autonomous cabin station provides take-off and landing, charging and data interaction services.

[0016] Therefore, the intelligent obstacle avoidance method and control system for unmanned aerial vehicle patrol along the traffic line in the application have the following beneficial technical effects: (1) By fusing multiple airborne sensor data (such as visual sensor, laser radar, millimeter wave radar, inertial measurement unit, etc.), the application can construct a high-precision environment cognition model to perceive static and dynamic obstacles along the traffic line in real time. Compared with the obstacle avoidance method of a single sensor, multi-source data fusion significantly improves the accuracy and reliability of obstacle identification, especially in complex environments and adverse weather conditions.

[0017] (2) The application adopts a hybrid decision algorithm to synchronously process the preset flight rules and the real-time perceived obstacle information, and generate optimal flight control instructions. The algorithm not only considers flight safety, but also takes into account flight efficiency and comfort. Through a multi-objective optimization framework, the system can dynamically adjust the obstacle avoidance strategy while complying with the flight rules, ensuring the safe flight of the UAV in complex environments. For example, when the wind reaches level 7 or above, the system will automatically generate automatic landing instructions or instructions that only allow forward flight, prohibiting flight towards the direction close to the traffic line, significantly improving flight safety.

[0018] In the hybrid decision algorithm of the application, the weights of the rule compliance cost and the obstacle avoidance cost can be dynamically adjusted based on environmental risk factors. This dynamic adjustment mechanism enables the system to maintain optimal obstacle avoidance performance in different environmental conditions. In high-risk environments, the system will tend to comply with flight rules and avoid high-risk maneuvers, thereby improving flight safety and reliability.

[0019] (3) Through data association algorithms and Bayesian filtering, the application can update the environmental cognition model in real time, ensuring that the UAV's perception of the surrounding environment is always up to date. This closed-loop decision update mechanism enables the UAV to quickly respond to environmental changes and adjust the flight path in time to avoid collision risks. For example, when a newly observed obstacle matches an existing obstacle, the system updates the state estimation of the obstacle, recalculates the cost function, and generates new control instructions to ensure the safety and effectiveness of the flight path.

[0020] (4) The application generates electronic fence data by defining flight corridors and their boundaries, ensuring that the UAV flies within a safe area. This preset flight rule not only improves flight safety, but also optimizes the flight path, reduces unnecessary detours, and improves patrol efficiency. For example, the UAV will automatically avoid no-fly zones close to traffic lines during flight, and can quickly adjust the path when encountering obstacles to continue the patrol task. BRIEF DESCRIPTION OF DRAWINGS

[0021] Figure 1 Flowchart of the intelligent obstacle avoidance method for UAV patrol along the traffic line of the application; Figure 2 Schematic diagram of the environmental cognition model. DETAILED DESCRIPTION

[0022] The technical solutions of the application are further described below through the drawings and examples.

[0023] Unless otherwise defined, the technical terms or scientific terms used in the application should be understood in their usual sense by those skilled in the art to which the application belongs.

[0024] Example 1 like Figure 1 As shown, the intelligent obstacle avoidance method for drone patrols along transportation routes includes the following steps: Step S1: Define the flight corridor and its boundaries for the target traffic route, and generate electronic fence data, including: The flight corridor is located within 200 meters outward from the roadbed of the transportation route (i.e., the drone flies within 200 meters along one side of the transportation route). Using the centerline of the traffic route as a reference, extend 100 meters to the patrol side (the side furthest from the core area of ​​the traffic route) as the baseline. ; From the baseline Offset 90 meters away from the traffic line to generate the outer boundary line of the corridor. ; From the baseline Offset 90 meters towards the traffic line to generate the inner boundary line of the corridor. ; And the inner boundary line The closest distance to the traffic route is 10 meters (meaning drones are prohibited from entering within 10 meters of the traffic route). This creates a 180-meter-wide flight corridor (the distance from the outer boundary to the inner boundary).

[0025] baseline The function expression is constructed based on the survey data of the traffic routes: ; in, Represents the slope of a straight line. Represents the horizontal axis coordinate. Represents the y-intercept of the line. Indicates control points, Indicates the total number of control points. Indicates the first One sampling point, Describes the cubic B-spline basis functions. Indicates parameter variables.

[0026] The geometric information of the flight corridor is equivalent to electronic fence data, including baselines. Function expression, outer boundary line and inner boundary line Location parameters and boundary tolerances .

[0027] Drones may fly in a direction away from traffic lines (outwards), but are prohibited from crossing in a direction close to traffic lines. When the wind is 7 or above, the UAV can automatically land or fly forward, and is prohibited from flying towards the direction close to the traffic line.

[0028] In step S2, the patrol UAV collects the on-board sensor data, and fuses the data with the electronic fence data, the positioning data and the external environment data to construct an environment cognition model, such as Figure 2 .

[0029] The on-board sensor data includes: image sequences collected by a vision sensor , point cloud data collected by a laser radar , radar point traces collected by a millimeter wave radar , and body angular velocity and acceleration collected by an inertial measurement unit. The positioning data includes: the UAV geodetic coordinates obtained through a global navigation satellite system real-time differential technique , the altitude , and high-frequency and high-precision pose information solved after fusing the inertial measurement unit data , represents the latitude, represents the longitude, , y , z respectively represent three-dimensional space coordinates, represents the roll angle, represents the pitch angle, represents the yaw angle. The external environment data includes: monitoring data uploaded by fixed perception nodes along the line and received from the ground control center , the monitoring data specifically includes real-time video frames shot by cameras along the line, heat source information detected by infrared sensors, abnormal vibration signals collected by vibration sensors, and line deformation data returned by fiber strain sensors; and fine wind speed vectors and precipitation data covering the patrol path obtained from a meteorological data service interface.

[0030] The specific process of constructing the environment cognition model is as follows: Through a multi-source data fusion filter, the on-board sensor data, the positioning data and the external environment data are time-space synchronized and unified in the coordinate system.

[0031] Time synchronization: taking the PPS second pulse signal output by the UAV global navigation satellite system module as the reference time mark, the timestamps of various sensor data are calibrated, and the sampling delays of different devices are compensated through linear interpolation, so that all data are aligned to the same time axis.

[0032] Coordinate unification: point cloud data acquired by lidar Radar traces acquired by millimeter-wave radar The image sequence is transformed from the sensor coordinate system to the body coordinate system using a rigid body transformation matrix, and then further transformed to the geodetic coordinate system WGS84 using pose information; Projecting the monitoring data to the geodetic coordinate system using the transformation relationship between the camera's intrinsic and extrinsic parameter matrices and the body coordinate system; The coordinates of the fixed sensing nodes are converted to the geodetic coordinate system.

[0033] Clustering and feature extraction are performed on the fused perception data to identify a set of static obstacles. and dynamic obstacle set The specific process is as follows: Clustering: The density-based clustering algorithm DBSCAN is used to cluster the 3D point cloud data in the geodetic coordinate system, and a neighborhood radius is set. =0.5 meters, minimum number of points MinPts=5, aggregate spatially adjacent points into candidate obstacle clusters. Feature extraction: Calculate the volume for each obstacle cluster. Surface area Centroid coordinates and average speed . Dynamic judgment: When the average velocity of the obstacle cluster A speed greater than 0.3 m / s and a rate of change of velocity less than 5% over three consecutive sampling periods are considered dynamic obstacles. Otherwise, it is judged as a static obstacle. .

[0034] for Every obstacle in By combining its historical trajectory with the body motion parameters of the inertial measurement unit, its velocity vector is estimated. And predict its future Trajectory over time . Ultimately, the environmental cognition model It is expressed as a tuple containing the following elements: .

[0035] Step S3: Based on the environmental cognition model, a hybrid decision-making algorithm is used to simultaneously process preset flight rules and real-time perceived obstacle information to generate flight control commands, including the following steps: Step S31: Calculate the cost of rule compliance: Current position of the computer body To the nearest corridor boundary ( represents the corridor boundary, is or ) Euclidean distance , and defines a rule-abiding cost function : ; wherein, , both represent scaling coefficients; This function ensures that when the UAV approaches or exceeds the boundary, the value increases sharply, and a larger value is set for the approach to the traffic line to strictly limit the flight in the direction of approaching the traffic line.

[0036] Step S32, calculate obstacle avoidance cost: for each obstacle in the environment awareness model , calculate its collision risk with the body, and integrate to obtain the total obstacle avoidance cost : ; wherein, represents the current distance between the body and the th obstacle, represents the risk coefficient set according to the obstacle type and relative speed, represents a very small positive value, used to prevent division by zero error.

[0037] Step S23, multi-objective cost function optimization: convert the generation problem of flight control instructions into a multi-objective optimization problem, and the cost function is: ; wherein, represents the cost of measuring flight comfort, represents the weight of the rule-abiding cost, represents the weight of the obstacle avoidance cost, represents the weight of the flight comfort cost.

[0038] Solve online by gradient descent method or model predictive control framework to obtain the optimal control instruction sequence that minimizes , and take the first instruction as the flight control instruction at the current time. When wind force reaches 7 or above, generate an automatic landing instruction or an instruction that only allows forward flight, prohibiting flight in the direction of approaching the traffic line.

[0039] The weights of the rule-abiding cost and the obstacle avoidance cost are dynamically adjusted based on the environmental risk factor: ; ; wherein, represents the baseline weight of the rule compliance cost, represents the baseline weight of the obstacle avoidance cost, , all represent the adjustment coefficient, represents the environmental risk factor; The environmental risk factor is calculated as follows: ; wherein, , represent the weighting coefficient.

[0040] This strategy makes the system more inclined to comply with the rules and stick to the preset path in harsh environments, rather than performing high-risk maneuver to avoid obstacles, especially when the wind reaches 7 levels and above, significantly improving to strictly limit the flight direction close to the traffic line.

[0041] When solving the cost function, the trajectory is taken as a constraint condition into the optimization framework, and the specific process is as follows: Set the prediction time domain , for each dynamic obstacle , extract its trajectory point set , represents the time variable, represents the current time; Define the candidate trajectory point set of the UAV in the prediction time domain as , represents the candidate position of the UAV at time, which is generated by the control command sequence to be solved. Establish collision constraints: for all and , require and Euclidean distance ≥ , represents the preset safety distance. Establish corridor constraints: for all , require to be located between and , and the distance to is not less than 0 (i.e. prohibit crossing towards the direction close to the traffic line).

[0042] The collision constraint and the corridor constraint are embedded in the optimization solving process of the multi-objective cost function, the constraint conditions are converted into cost items by the Lagrange multiplier method, or the candidate solution that violates the constraint is punished in the gradient descent iteration, so that the generated future instruction sequence meets the safety and rule requirements in the whole prediction time domain.

[0043] Step S4, the flight control instruction is executed, and the environment cognition model is updated in real time based on the perception feedback.

[0044] The environment cognition model is updated in real time based on the perception feedback, including: The new observation data and the existing obstacles are matched by a data association algorithm, and the state estimation of the obstacles is updated by a Bayesian filter; After refreshing the environment cognition model, the cost function is recalculated and the new control instruction is solved to realize closed-loop decision updating.

[0045] An intelligent patrol control system for implementing the above method, comprising: The patrol unmanned aerial vehicle is equipped with a sensor unit, a computing unit, a positioning unit and a communication unit; The sensor unit is used for collecting airborne sensor data; The positioning unit is used for obtaining the geodetic coordinates, altitude and pose information of the unmanned aerial vehicle; The communication unit is used for data interaction with the ground control center and the distributed autonomous cabin station; The computing unit is used for running a hybrid decision algorithm, generating flight control instructions in real time according to the environment cognition model, and when wind force reaches 7 or above, controlling the unmanned aerial vehicle to automatically land or only allowing forward flight, prohibiting flight towards the direction close to the traffic route; The ground control center is used for configuring and issuing electronic fence data and task instructions; The distributed autonomous cabin station provides take-off and landing, charging and data interaction services.

[0046] It is worth noting that the contents not elaborated in the present application are all prior art and are well known to those skilled in the art.

[0047] Therefore, the intelligent obstacle avoidance method and control system for unmanned aerial vehicle patrol along the traffic route can effectively improve the obstacle avoidance ability and patrol efficiency of the unmanned aerial vehicle in complex environment, ensure flight safety, and are suitable for efficient patrol tasks along the traffic route.

[0048] It should be pointed out finally that the above examples are only used to illustrate the technical solutions of the present application but not to limit it, and although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solutions of the present application can still be modified or replaced equivalently, and these modifications or equivalent replacements should not make the modified technical solutions deviate from the spirit and scope of the technical solutions of the present application.

Claims

1. An intelligent obstacle avoidance method for unmanned aerial vehicle patrol along a traffic route, characterized in that, The method comprises the following steps: Step S1, defining a flight corridor and its boundary for a target traffic line, and generating electronic fence data; Step S2, collecting airborne sensor data by a patrol unmanned aerial vehicle, and fusing the airborne sensor data with electronic fence data, positioning data and external environment data to construct an environment cognition model; Step S3, based on the environment cognition model, using a hybrid decision algorithm to synchronously process preset flight rules and real-time perceived obstacle information, and generating flight control instructions; Step S4, executing the flight control instructions, and updating the environment cognition model in real time based on perception feedback. 2.The intelligent obstacle avoidance method for UAV patrol along a traffic route according to claim 1, wherein, In step S1, the flight corridor is located within a range of 200 meters extending outward from the roadbed of the traffic line, and the electronic fence data is generated by defining the flight corridor and its boundary for the target traffic line, comprising: The flight corridor is located within a range of 200 meters extending outward from the roadbed of the traffic line; The center line of the traffic line is taken as the reference, and the reference line is extended 100 meters to the patrol side ; from the datum offset 90 meters from the traffic route direction, generating the outer boundary line of the corridor ; from the datum offset 90 meters in the direction of the traffic route, generating the inner boundary line of the corridor ; and the inner boundary line The nearest distance to the traffic route is 10 meters; Thus, a flight corridor with a width of 180 meters is formed; reference line The functional expression of the reference line is constructed based on survey data of the traffic route: ； wherein, represents a straight line slope, represents a horizontal axis coordinate, represents a straight line vertical axis intercept, represents a control point, represents a total number of control points, represents an th sampling point, represents a cubic B-spline basis function, represents a parameter variable; The geometry information of the flight corridor is the electronic fence data, including the function expression of the reference line , the position parameters and boundary tolerance of the outer boundary line and the inner boundary line . ​ 3.The intelligent obstacle avoidance method for UAV patrol along a traffic route according to claim 1, wherein, In step S2, the on-board sensor data comprises: an image sequence captured by a vision sensor point cloud data captured by a lidar radar tracks captured by a millimeter wave radar and body angular velocity and acceleration captured by an inertial measurement unit The positioning data includes: unmanned aerial vehicle geodetic coordinates , altitude , pose information , wherein represents the latitude, represents the longitude, , y , z respectively represent three-dimensional space coordinates, represents the roll angle, represents the pitch angle, represents the yaw angle; The external environment data includes monitoring data uploaded by the fixed perception nodes , a wind speed vector , and precipitation data The monitoring data includes real-time video frames captured by cameras along the line, heat source information detected by infrared sensors, abnormal vibration signals collected by vibration sensors, and line deformation data returned by fiber strain sensors. 4.The intelligent obstacle avoidance method for UAV patrol along a traffic route according to claim 1, wherein, In step S2, the specific process of constructing the environment cognition model is as follows: Through a multi-source data fusion filter, the airborne sensor data, the positioning data and the external environment data are synchronized in time and space and unified in the coordinate system; Clustering and feature extraction are performed on the fused perception data to identify a set of static obstacles. and dynamic obstacle set The specific process is as follows: Clustering processing: the density clustering algorithm DBSCAN is used to cluster the three-dimensional point cloud data in the geodetic coordinate system, the neighborhood radius is set to 0.5 meters, the minimum number of included points MinPts is set to 5, and the points adjacent in space are aggregated into a candidate obstacle cluster. =0.5 meters, the minimum number of included points MinPts is set to 5, and the points adjacent in space are aggregated into a candidate obstacle cluster. Feature extraction: compute volume, surface area, centroid coordinates, and average velocity for each obstacle cluster ;​​​ Dynamicity judgment: when the average speed of the cluster of obstacles > 0.3 m / s and the speed change rate is less than 5% in the last 3 sampling periods, it is determined as a dynamic obstacle ; otherwise, it is determined as a static obstacle ; For each obstacle in , its velocity vector is estimated by combining its historical trajectory with the body motion parameters of the inertial measurement unit and its future trajectory is predicted for a certain time horizon; Ultimately, the environmental awareness model is expressed as a tuple comprising the following elements: 。 5.The intelligent obstacle avoidance method for UAV patrol along a traffic route according to claim 1, wherein, In step S3, based on the environment cognition model, a hybrid decision algorithm is used to synchronously process preset flight rules and real-time perceived obstacle information, and flight control instructions are generated, comprising the following steps: Step S31, current position of the computer body Euclidean distance to the nearest corridor border and define a rule compliance cost function :​ ； wherein , both represent scaling coefficients; Step S32, for each obstacle in the environment awareness model , calculate its collision risk with the body , and get the total obstacle avoidance cost : ； wherein, represents the current distance of the machine from the represents a risk factor set according to the obstacle type and relative speed, represents a positive value;​ Step S23, the generation problem of flight control instructions is converted into a multi-objective optimization problem, whose cost function is: ； wherein, represents a cost of measuring flight comfort, represents a weight of the cost of rule compliance, represents a weight of the cost of obstacle avoidance, represents a weight of the cost of flight comfort; By solving online using gradient descent or model predictive control framework, we can obtain the solution that... The optimal control command sequence is minimized, and the first command is taken as the flight control command at the current moment. When the wind force is detected to reach level 7 or above, an automatic landing command or a command that only allows forward flight is generated, and flight towards traffic routes is prohibited. 6.The intelligent obstacle avoidance method for UAV patrol along a traffic route according to claim 1, wherein, In step S3, the weights of rule compliance cost and obstacle avoidance cost are dynamically adjusted based on the environmental risk factor: ； ； wherein, represents a reference weight of a rule compliance cost, represents a reference weight of an obstacle avoidance cost, , each represents a regulation coefficient, represents an environmental risk factor; The environmental risk factor is calculated as follows: ； wherein , denotes a weighting factor. 7.The intelligent obstacle avoidance method for UAV patrol along a traffic route according to claim 1, wherein, When solving the cost function, the trajectory The constraints are incorporated into the optimization framework as follows: Setting a prediction horizon , for each dynamic obstacle , extracting a set of trajectory points thereof within the prediction horizon , denotes a time variable, denotes the current time instant; The candidate trajectory point set of the UAV in the prediction time domain is defined as , represents the candidate position of the UAV at the moment Establish collision constraints: for all and , require Euclidean distance of ≥ , denotes a preset safety distance; Establish corridor constraints: for all , require to be between and , and distance to is not less than 0; The collision constraint and the corridor constraint are embedded in the optimization solving process of the multi-objective cost function, and the constraint conditions are converted into cost items by the Lagrange multiplier method, or a penalty is imposed on the candidate solutions that violate the constraints in the gradient descent iteration, so as to ensure that the generated future instruction sequence meets the safety and rule requirements in the entire prediction time domain. 8.The intelligent obstacle avoidance method for UAV patrol along a traffic route according to claim 1, wherein, In step S4, the environment cognition model is updated in real time based on perception feedback, comprising: Through a data association algorithm, new observation data is matched with existing obstacles, and a Bayesian filter is used to update the obstacle state estimation; After refreshing the environment cognition model, the cost function is recalculated and a new control instruction is solved to realize closed-loop decision updating.

9. An intelligent guard control system for implementing the method of any one of claims 1-8, characterized by It comprises: A patrol unmanned aerial vehicle, which is equipped with a sensor unit, a computing unit, a positioning unit and a communication unit; The sensor unit is used to collect airborne sensor data; The positioning unit is used to obtain the geodetic coordinates, altitude and pose information of the unmanned aerial vehicle; The communication unit is used for data interaction with a ground control center and a distributed autonomous cabin station; The computing unit is used to run a hybrid decision algorithm to generate flight control instructions in real time according to the environment cognition model, and when wind force reaches 7 or above, the unmanned aerial vehicle is controlled to automatically land or is only allowed to fly forward, and is prohibited to fly towards the direction close to the traffic line; The ground control center is used to configure and issue electronic fence data and task instructions; The distributed autonomous cabin station provides take-off and landing, charging and data interaction services.

Images