407 results about "Path tracking" patented technology

The invention relates to the crossing field of mechanical engineering and automatic control, in particular to a global path planning and anti-swing control method for a ship unloader, and aims to solve the problems of rigid path planning and poor synergism of out-of-control swing of a lifting appliance in traditional ship unloading operation. The method comprises the following steps: constructing a dynamic three-dimensional operation space model with fusion of a laser radar and binocular vision, and updating obstacle information in real time; an improved fast extended random tree algorithm is adopted to generate a high-smoothness initial path; establishing a six-degree-of-freedom lifting appliance swinging dynamic model and identifying parameters on line; path tracking and anti-swing torque are synchronously optimized through a model prediction controller, and the control period is smaller than or equal to 20 milliseconds; and closed-loop feedback correction is implemented by combining an encoder and an inertial measurement unit. According to the scheme, environment dynamic sensing, path-anti-swing depth cooperation and multi-disturbance self-adaptive compensation are achieved, the operation rhythm is improved by 30% or above, the system still operates stably under the 8-level wind condition, and high precision, high robustness and engineering implementability are achieved.

The invention relates to the technical field of autonomous navigation of inspection robots, and provides a field inspection robot autonomous navigation and path planning method based on multi-modal sensing. The method comprises the following steps: collecting a laser radar point cloud, a camera image, inertial measurement and positioning data, obtaining an environment semantic feature set through spatio-temporal feature fusion, and generating a semantic occupation map; inputting the current position of the robot, the target point and the semantic occupation map into a trajectory generation network to obtain candidate trajectories meeting obstacle avoidance and path smoothness constraints, and completing task sorting and trajectory splicing in combination with inspection task points to form a global path; in the operation process, the reinforcement learning control model adjusts the linear speed and the angular speed in real time, and path tracking and dynamic obstacle avoidance are achieved. The navigation precision and the operation safety of the inspection robot in the complex field area are improved.

The invention discloses an automatic driving path planning method based on multi-sensor fusion, and relates to the technical field of automatic driving, and the method comprises the steps: collecting environment, vehicle and positioning data through multi-source sensors, such as a laser radar and a camera; mapping a vehicle body coordinate system through coordinate conversion, and carrying out downsampling, correction enhancement and denoising preprocessing on data; extracting multi-sensor features, and distributing weights by means of a cross-modal attention mechanism to complete multi-modal fusion; recognizing obstacles and passable areas, and predicting a 5s track of a dynamic obstacle; 5-8 initial paths are generated based on the coordinate system and dynamic constraints; constructing a multi-objective function to screen an optimal path; and finally, a steering angle and an acceleration instruction are calculated through model prediction control, and accurate path tracking is realized. The sensing robustness is improved through multi-sensor fusion, the dynamic weight adjustment adapts to the complex environment, the emergency obstacle avoidance mechanism is quick in response, and the automatic driving reliability and the scene adaptability are integrally enhanced.

The invention belongs to the technical field of track planning, and particularly relates to a track planning method for a track and non-track mixed region, and the method comprises the steps: dynamically distributing a path point sequence for an automatic guided vehicle, and switching a control mode according to the type of a region where a current target point is located: generating a first control instruction for path tracking in a track region; in the non-orbital area, the pose and curvature of the exit of the previous orbital area are used as initial reference quantities to plan a smooth trajectory, and a second control instruction is generated; constraint shaping is carried out on the first control instruction, the second control instruction is adjusted, it is ensured that the end point state of path tracking and the starting point state of trajectory planning meet the continuity rules of the position, the course and the curvature at the joint point of the two areas, and finally the instructions are sent to corresponding control loops to be executed. According to the invention, smooth and coherent navigation control of the automatic guided vehicle between the fixed track and the free driving area is realized.

The invention provides an ocean current interference resistant fault-tolerant control method and system for a robot multi-motor propulsion system, and the method comprises the steps: inputting the actual and expected position error and speed error of an underwater robot into a self-adaptive backstepping sliding mode path tracking controller, and obtaining the thrust needed by tracking motion; introducing a propeller weight matrix representing the fault degree of the propeller into a weighted pseudo-inverse method, optimizing the propeller weight matrix by adopting an intelligent algorithm to obtain an optimal propeller weight matrix, and performing thrust distribution on thrust required by tracking motion through the weighted pseudo-inverse method to obtain a thrust distribution result; according to the operation and thrust distribution results of the multiple motors, the parameters of all the motors are adjusted in a self-adaptive mode through a multi-motor fault-tolerant control strategy; and each motor remotely controls the underwater robot based on the parameters after self-adaptive adjustment, and obtains the actual position and speed of the underwater robot at the current moment for loop closing.

The invention relates to the technical field of intelligent sensors, in particular to a workshop harmful gas abnormity monitoring method and system based on multi-modal data, and the method comprises the following steps: obtaining the multi-period concentration change of a node, recognizing the reverse direction, forming a bounce fragment, combining node behaviors according to the correlation of time and space, and constructing a diffusion path; and in combination with node toxicity residence and trend change and gas and time information at the convergence position, a workshop multi-modal toxicity anomaly monitoring result is obtained. According to the method, gas fluctuation characteristics are captured by recognizing the concentration change direction and the reversal amplitude, a behavior combination is constructed by combining time and space information, the linkage recognition capability between nodes is enhanced, a path sequence is constructed by depending on the trend direction and the node sequence to present a diffusion track, and extension and mutation nodes are extracted by superposing the residence state and the change trend. The dynamic monitoring range of toxic gas in multiple scenes is expanded, and correlation analysis of behavior traceability, path tracking and abnormal gathering areas is supported.

The invention discloses a reinforcement learning unmanned ship path control method based on double-track regulation and control random network distillation. The method comprises the operation steps that an unmanned ship builds a path tracking simulation environment and a kinetic model; the unmanned ship builds a core algorithm flexible action evaluation algorithm framework; the unmanned ship deploys a priority experience playback pool based on quality and success guidance; an uncertainty perception and risk perception mechanism is introduced into the unmanned ship; the unmanned ship builds a success rate-based reward attenuation and cold start module, and the unmanned ship calculates a total reward and designs a reward softening mechanism to smooth the total reward; the unmanned ship imports hyper-parameters of all the modules, starts training circulation in a simulation environment, and dynamically adjusts exploration intensity and the like; according to the method, uncertainty and risk indexes are introduced, the exploration intensity of the intelligent agent is controlled, the intelligent agent is prevented from making dangerous actions, and the robustness is improved; a priority experience playback pool based on quality and success guidance is introduced, high-quality samples are better played back, and strategy convergence is accelerated.

The invention provides a business path tracking and fault tracing method and device for a video monitoring system, and relates to the technical field of video monitoring fault diagnos.The video monitoring system is divided into a plurality of layers, and multiple types of data acquisition probes are deployed at key nodes of each layer; when a user initiates a video request, generating a Trace ID to be spread along with a video streaming signaling, and reconstructing an end-to-end service path in combination with node information captured by a probe; associating and fusing the multi-dimensional performance data by taking the TraceID as a key, and establishing an end-to-end total delay decomposition and dynamic health baseline; and positioning a root cause node based on the weighted directed graph, the node anomaly confidence score and the fault propagation consistency, displaying a path, data and a traceability result through a visual interface, and generating a precise alarm. According to the method, service link visualization is realized, traditional equipment alarm is upgraded to service fault root cause positioning, the troubleshooting efficiency is improved, and the method is suitable for an isomerized large-scale video monitoring system.

The invention provides a ship path tracking and rolling comprehensive control method and device based on a straight-wing propeller, belongs to the technical field of ship motion control, and solves the technical problem that path tracking and rolling control precision and efficiency of a ship are insufficient due to environmental disturbance. Constructing a four-degree-of-freedom ship motion equation, constructing a four-degree-of-freedom ship motion model with interference and measurement noise, reconstructing a ship motion state by adopting a Kalman filter, calculating a path tracking error by utilizing a self-adaptive sight guidance algorithm, and generating an expected course angle; determining a longitudinal thrust, a rolling stabilizing moment and a course control thrust; and the revolution speed and the rotation swing angle of the straight wing propeller are optimized, and the rotation swing angle is recalculated. The method is suitable for the ship provided with the straight-wing propeller, and high-precision path tracking and efficient rolling stabilization are achieved by controlling the revolution speed and the swing angle of the propeller.

The invention relates to the technical field of agricultural informatization and supply chain risk control, and particularly discloses an agricultural supply chain risk intelligent sensing and early warning system based on multi-source data fusion. According to the system, six multi-source data including a producing area environment, an agricultural product category, a transaction behavior, a logistics link, credit and market information are integrated through a data acquisition layer; space-time alignment and cleaning are carried out through the data processing and alignment layer; through feature engineering and a multi-source fusion layer, depth features are constructed by comprehensively utilizing a knowledge graph and a graph attention network, Transform behavior sequence modeling, CNN-LSTM remote sensing time sequence analysis and Graph2Seq logistics trajectory prediction, and the Transform and the graph attention network are specially adapted for an agricultural scene; the dynamic risk scoring layer is used for comprehensively calculating five risks of producing areas, logistics, transactions, markets and credit, and a comprehensive risk score is output through weighted fusion; a decision basis is provided by integrating SHAP, attention visualization and map path tracking through an interpretability output layer; and finally, outputting a grading risk strategy by a strategy decision-making layer. According to the invention, dynamic, accurate and explainable intelligent assessment and early warning of full-link and multi-dimensional risks of the agricultural supply chain are realized.

The invention discloses an automatic path tracking method and system for a crawler-type combine harvester, and belongs to the technical field of unmanned driving of agricultural machinery, and the method comprises the following steps: automatic on-line: obtaining a current position and a current course, carrying out transverse deviation calculation and judgment, adjusting the advancing direction of the harvester, and enabling the harvester to be on-line rapidly; linear path tracking: calculating a transverse deviation and a course deflection angle in real time and finely adjusting the harvester; performing current operation path termination judgment: performing distance judgment, angle judgment and area judgment on the current position of the harvester to obtain a current operation path termination judgment result, and determining whether the harvester reaches the terminal point of the current operation path or not; and right-angle turning: performing right-angle turning to realize accurate line feed operation of the harvester. According to the invention, the problem that the working efficiency is low due to the fact that the existing tracked vehicle cannot quickly go on line and control right-angle turning is solved. According to the method, high-precision path tracking is ensured, and meanwhile, the working efficiency and the stability of a control system are improved.

The invention discloses a container terminal truck intelligent scheduling method and system based on multiple driving modes. The method comprises the steps that a whole-process system architecture integrating a central scheduling platform, a vehicle-mounted intelligent terminal and a sensing and communication network is constructed; the method comprises the following steps: acquiring basic data of vehicles, tasks, road networks and environments, constructing a multi-objective optimization function, establishing a dangerous goods risk integral model, respectively setting mathematical constraints for task assignment, path planning, hybrid driving coordination, dynamic path tracking and mode switching, and forming a multi-dimensional mathematical model; an improved non-dominated sorting genetic algorithm is adopted to solve the model, and a personalized scheduling scheme including vehicle-task assignment, path planning, time requirements and risk control rules is generated; through cooperation of the central scheduling platform and the vehicle-mounted intelligent terminal, MPC dynamic path tracking is adopted for the unmanned vehicle, visual and voice dual-mode guidance is provided for the artificial vehicle, and hybrid driving cooperative management and control are implemented, so that the vehicle operation efficiency and the dangerous goods transportation safety are guaranteed.

The invention discloses an emergency homeward voyage control method for an unmanned aerial vehicle under a power failure condition and a medium. The method comprises the following steps: constructing a cascade PID path tracking controller; constructing a cascade model prediction path tracking controller; constructing a model prediction path tracking controller based on the extended state observer; a controller is determined according to the unmanned aerial vehicle power fault condition of emergency return, the unmanned aerial vehicle flight state, forced landing point information and external environment factors, and emergency return control is achieved. The emergency return path tracking controller is determined according to the return route provided by the current flight state, and the return route is tracked.

The invention discloses a transformer substation AC power supply residual current detection method and device, and the method comprises the steps: carrying out the vector synthesis of three-phase current data and zero line current data, forming a current difference sequence, exporting a residual current reference curve, and carrying out the fluctuation analysis of the residual current reference curve, and judging the leakage characteristics. After effective leakage features are formed through harmonic elimination, dominant frequency components are locked through frequency spectrum decomposition; calibrating a leakage type identifier according to the dominant frequency component and forming segmented leakage distribution; a deviation degree is formed by means of segmented leakage distribution and residual current reference curve deviation analysis, a correction deviation value is formed through load fluctuation compensation, and a standard exceeding coefficient is formed according to threshold value comparison to detect abnormal nodes to form hidden danger data; establishing a judgment rule based on the hidden danger data and the leakage type identifier to form a detection evaluation index; and executing path tracking on the detection evaluation indexes to form leakage position information, forming a disposal priority through intensity analysis to generate a residual current detection report, and realizing leakage current classification identification and self-adaptive evaluation.

Approaches presented herein provide systems and methods for path tracing using a set of textured spherical surfaces obtained from an importance map for an image. An image representation may be generated using the importance map and evaluated to identify a first set of nodes. The nodes may have associated values, such as luminance values, that may be used to subdivide the nodes into bins to maintain a weighed distribution for the associated values. An array of nodes may be generated for sampling and conversion to a three-dimensional direction that may be applied to one or more lighting effects.

The invention relates to an underwater snakelike robot single propeller cooperative control method based on reinforcement learning, and the method comprises the steps: building an underwater snakelike robot structure model, and constructing an underwater snakelike robot motion control and decision model; a state space and an action space are defined, snake body multi-joint wave propulsion from a central pattern generator and thrust output of a tail propeller are uniformly incorporated into a control decision framework, and a composite reward function with path tracking errors, course deviation and propulsion efficiency as targets is designed. Training an underwater snakelike robot motion control and decision model based on a reinforcement learning algorithm, and generating an optimal underwater snakelike robot cooperative control strategy to execute a multi-waypoint path tracking task of the underwater snakelike robot, so that the underwater snakelike robot can be tracked under the condition of not depending on an accurate hydrodynamic model; and a cooperative control strategy of joint waveform parameters and thruster thrust is autonomously learned, so that stable and high-precision path tracking of the super-redundant underwater snakelike robot under the constraint of multiple sections of paths including turning road sections is realized.

The invention belongs to the technical field of leakage detection, and particularly relates to an existing building basement side wall leakage three-dimensional detection system and method based on an intelligent wall-climbing robot. The detection system comprises an intelligent wall-climbing robot platform, a multi-modal detection sensor group, a data processing and analysis system and a user interaction terminal, wherein the multi-modal detection sensor group is carried on the intelligent wall-climbing robot platform; the intelligent wall-climbing robot platform comprises a moving adsorption system, a moving mechanism, a positioning navigation system, a posture adjusting mechanism and a communication power supply device. The multi-modal detection sensor group comprises an infrared thermal imager, a high-resolution visible light camera, a 3D laser scanner, a wall penetrating radar, a capacitive humidity sensor and an ultrasonic thickness gauge; the data processing and analysis system comprises an edge computing unit and a cloud analysis platform; the edge calculation unit is responsible for real-time data acquisition, preprocessing, sensor control and motion control. According to the existing building basement side wall leakage three-dimensional detection system and method based on the intelligent wall-climbing robot, full-thickness detection coverage from the surface layer to the deep layer, conversion from manual operation to full-automatic wall climbing and crossing from single-point detection to path tracking are achieved.

The invention discloses a path tracking and stability-oriented chassis multi-system cooperative game control method, and belongs to the technical field of vehicle dynamics control, chassis multiple systems comprise a DYC system, an AFS system, an ARS system and an ASS system, and the method comprises the steps of constructing a vehicle dynamics and path tracking cooperative control model and establishing a vehicle state prediction equation; the DYC system, the AFS system, the ARS system and the ASS system serve as participants of the cooperative game, a total cost function is constructed, and the control weight of each participant is dynamically adjusted according to the real-time vehicle state; and performing distributed solution on the total cost function by adopting an ADMM algorithm to obtain optimal control input of the DYC system, the AFS system, the ARS system and the ASS system. According to the method, the optimal balance between the path tracking precision and the driving stability is realized while the calculation efficiency is ensured, so that the high-performance control of the intelligent vehicle under the limit working condition is realized.

An intelligent vehicle active obstacle avoidance control method based on visual perception is used for improving the driving safety of a vehicle in a complex traffic scene. The invention relates to the field of intelligent driving. The system comprises an upper layer and a lower layer, the upper layer is an environment sensing module, and the lower layer comprises a risk assessment module, a path planning module and a pure tracking algorithm. The upper-layer environment sensing module comprises RRW-YOLOv11n, multi-scale features are extracted through an RGCEBlock module, feature fusion is enhanced through a Re-calibration FPN structure, the bounding box regression precision is optimized by using a WPIOU loss function, and finally sensing information is output; a lower-layer risk assessment module performs multi-source risk assessment to obtain a multi-source risk probability, calculates a posterior risk probability through Bayesian risk fusion, and plans a path through a path planning module; path tracking control is carried out through a pure tracking algorithm, and safe driving of the vehicle in a complex traffic scene is achieved.

The invention relates to a full-link differentiable physical enhancement type automatic driving control method and a full-link differentiable physical enhancement type automatic driving control system. The method comprises the following steps: constructing a full-link differentiable PERL dynamical model to reconstruct real vehicle dynamics in a high-fidelity manner; establishing a micro-preview PID execution layer, calculating a transverse error and a longitudinal speed error based on a dynamic preview distance, and generating a steering wheel angle instruction and an automobile longitudinal acceleration instruction by using a PID control law supporting gradient return; and the PID gain parameter and the preview distance are adaptively adjusted in real time by using the SAC network according to the current vehicle state. According to the full-link micro closed-loop training architecture designed by the invention, end-to-end optimization of control parameters is directly guided by utilizing gradient information of dynamic residual errors, the problem of distortion of a Sim2Real model is effectively solved, the physical interpretability and smoothness of a control strategy are ensured, and meanwhile, the optimal optimization of the control parameters is realized. The trained strategy network significantly improves the path tracking precision and robustness of the vehicle under a complex working condition.

The invention discloses an unmanned aerial vehicle image-assisted path tracking and obstacle avoidance method and system, and the method comprises the following steps: calling a multi-modal sensor group deployed on an unmanned aerial vehicle to collect environment data in response to a flight task instruction of the unmanned aerial vehicle, and carrying out the cross-modal data fusion of the environment data through an adaptive time synchronization algorithm; and calling a preset generative adversarial network model, performing image generation and illumination compensation on low-light image data in the fused environment data, and generating a target enhanced image close to a visible light environment. According to the invention, through cross-modal learning and self-supervised learning technologies, the perception and data synchronization capability of the unmanned aerial vehicle in a complex environment is improved. According to the invention, the generative adversarial network is adopted for image enhancement, and especially in a low-light environment, the accuracy of obstacle detection is improved; real-time obstacle detection and three-dimensional environment modeling are performed in combination with a deep learning model, and path planning and obstacle avoidance control are optimized through deep reinforcement learning.

The invention discloses a semiconductor chip test information automatic analysis system and method, and relates to the technical field of information analysis, and the method comprises the steps: calculating a parameter reference value according to a standardized test data set, carrying out the multi-dimensional discrimination feature extraction based on the parameter reference value, generating a test feature vector, and carrying out the analysis of the test feature vector; injecting the test feature vectors into the parameter influence network model, analyzing a dynamic interaction relationship among test parameters through an anomaly propagation simulation algorithm, performing root cause sorting and influence path tracking based on the dynamic interaction relationship, generating an anomaly analysis report, calling an intelligent diagnosis mechanism according to the anomaly analysis report, and performing fault diagnosis on the test parameters according to the intelligent diagnosis mechanism. Generating a structured conclusion through historical case library matching, and synchronously activating a visualization function to perform interactive presentation on the structured conclusion; according to the method, comprehensive representation of multi-dimensional discrimination information is realized through multi-dimensional feature extraction, the defect that an existing method is limited to single-parameter statistics is overcome, and the test feature vector expression capability is improved.

The invention discloses an unmanned surface vehicle time-varying formation pattern transformation control method based on area control, and the method comprises the steps: constructing an unmanned surface vehicle formation time-varying cooperation mechanism, constructing the path tracking and obstacle avoidance capability of a single unmanned surface vehicle, drawing up a potential field quantitative expression according to an obstacle environment, and determining a pattern transformation mode. The safety and flexibility of the formation system are evaluated, and the control method designed for the unmanned ship formation can ensure the safety and flexibility of obstacle avoidance and formation change. Through the method and the system, the navigation precision of the unmanned ship can be dynamically adjusted according to the environmental constraint and the change of the formation internal structure, the environmental adaptability of the unmanned ship individual is remarkably improved, and the flexibility of the time-varying formation and the diversity of task execution are also improved.

The invention relates to the technical field of operation monitoring and fault diagnosis, in particular to an intelligent power plant operation parameter online anomaly detection and diagnosis method, which comprises the following steps: S1, collecting operation parameters of a boiler, including temperature, steam pressure and feed water flow; s2, calculating a dynamic coupling strength value based on the operation parameters collected in the S1; s3, comparing with a preset standard range, identifying an abnormal coupling strength value exceeding a deviation range, and marking a corresponding abnormal parameter combination; s4, performing reverse path tracking through the parameter coupling relation map, and positioning root parameters causing abnormal coupling; and S5, matching a preset fault knowledge base to generate a diagnosis report. According to the invention, through organic combination of multi-parameter synchronous acquisition, dynamic coupling analysis, abnormity identification and traceability diagnosis, accurate monitoring of the operation state of the intelligent power plant boiler and rapid positioning of the fault are realized.

A critical path tracking system for an integrated circuit (IC) is described. The system may include a real critical path with a first set of combinatorial logic receiving data and clock inputs, generating a first output. The system may include a replica critical path with a second set of combinatorial logic replicating the first set, generating a second output. Capture flip-flops (CFFs) may be coupled to paths, capturing the first and second outputs at different points. A programmable delay element may introduce adjustable delays to the second output. A multiplexer may select between the first and delayed outputs for the CFFs, and a comparator may generate a path_failure_signature by comparing the outputs. A control circuit may dynamically adjust the delay settings and the IC's supply voltage based on the path failure signature. A software loop may read the signature, analyze timing margins, and control the circuit.

The invention relates to the technical field of vehicle control, and discloses a vehicle path tracking control method and device, equipment and a medium. The method comprises the steps that vehicle state actual measurement parameters of a vehicle under the current working condition are obtained; determining a transverse velocity compensation value and a yaw velocity compensation value corresponding to the vehicle state actual measurement parameters based on a Gaussian process regression method; compensating a preset vehicle expansion dynamical model based on the transverse velocity compensation value and the yaw velocity compensation value to obtain a target vehicle dynamical model; and generating a front wheel steering angle predicted value by using the target vehicle dynamics model based on a model prediction control method, and performing vehicle path tracking control based on the front wheel steering angle predicted value. According to the embodiment of the invention, the control precision and timeliness of vehicle path tracking control can be improved.

The invention provides an intelligent ship digital twinning motion modeling and parallel anti-interference path tracking controller. The intelligent ship digital twinning motion modeling and parallel anti-interference path tracking controller comprises a guidance signal module, a speed optimization module, a parallel path tracking controller module, a data-driven learning predictor module and an actual controller module. The data-driven learning predictor module receives position information, course angle information and speed information from the actual intelligent ship system module, and the data-driven learning predictor module receives parallel path tracking control force and torque from the parallel path tracking controller module; the data driving learning predictor module sends estimation information of the position and course angle of a virtual intelligent ship and estimation information of the speed of the virtual intelligent ship to the guidance signal module and the parallel path tracking controller module. According to the method, the self-adaptive capacity of the ship under the complex sea condition is enhanced, the collision risk is reduced fundamentally, and an effective solution is provided for the navigation scene with the high safety requirement.

The application relates to the technical field of intelligent driving, for example, to a path tracking control method and device based on intelligent driving and a vehicle. The control method comprises the following steps: acquiring running state information and planning path information of the vehicle; constructing a state space based on the running state information and the planning path information; inputting the state space into a reinforcement learning strategy model to obtain a vehicle speed sequence based on the planning path information; constructing and solving a control Lyapunov-barrier function based on the planning path information and the vehicle speed sequence to obtain an explicit control law; and controlling the vehicle to run based on the explicit control law. The present application uses a reinforcement learning algorithm to process road curvature and slope to output a globally optimized speed sequence. The lower layer constructs an explicit control target based on the speed reference sequence and the planning path information, and solves the explicit control law to generate a control instruction meeting the tracking accuracy and safety requirements, thereby realizing the autonomous driving function of the vehicle in a complex environment.

The invention discloses a composite steering unmanned platform stability control method based on an extension theory. According to the method, an upper-layer hierarchical control framework, a middle-layer hierarchical control framework and a lower-layer hierarchical control framework are constructed for a distributed driving composite steering unmanned platform. The upper-layer trajectory tracking controller adopts model predictive control (MPC) to output an expected yawing moment, and adjusts the longitudinal driving moment of each wheel in combination with PID to realize path tracking control; the middle layer adopts a Gaussian mixture model (GMM) based on a nonlinear tire model, solves an extension boundary threshold value on a phase plane through a maximum likelihood estimation algorithm, introduces an extension set correlation function, adaptively distributes Ackerman steering and differential steering weights according to a side slip angle and a change rate thereof, and realizes smooth switching and fusion of multi-mode steering; and the lower layer decouples and distributes the tire force, and realizes coordination and satisfaction of the yawing moment and the driving demand by combining the driving torque and the Ackerman steering angle inverse solution.

The invention belongs to the field of power systems and intelligent power grids, and discloses a self-adaptive depth disturbance perception and anti-interference identification guiding system which comprises a data preprocessing unit, a topology fusion unit, a depth disturbance analysis unit and a decision guiding unit. The data preprocessing unit is used for receiving multi-source real-time data of a power system and preprocessing the multi-source real-time data to extract key electrical characteristics related to disturbance. The topology fusion unit is used for receiving the key electrical characteristics, performing graph model modeling on the key electrical characteristics in combination with a power grid topology structure of the power system so as to generate fusion characteristics with electrical attributes and topological positions, and modeling a disturbance propagation path; the depth disturbance analysis unit comprises a disturbance classification and exploration module, a space positioning sub-network and a path analysis module; the problems that in the prior art, the unknown disturbance recognition capacity is insufficient, disturbance source positioning and propagation path tracking precision is low, and system response is lagged are effectively solved.