118 results about "Adaptive planning" patented technology

The invention provides an unmanned aerial vehicle optimal route planning method and system fusing image recognition and M-RRT and APF algorithms. The point cloud and visual data of a fan are obtained in real time through a multi-mode sensor, key parts of blades are recognized based on deep learning, a geometric mapping model is constructed, the blade tip points are corrected in a clustering mode in combination with DBSCAN, and the shutdown posture is predicted. A global path adopts an M-RRT algorithm improved by a direction heuristic factor to guide and search a key area of a blade; a local track is optimized through a dynamic weight APF algorithm, and a repulsive force field is adjusted in real time to cope with attitude changes. An online re-planning mechanism is introduced, NSGA-III multi-target optimization is triggered when the environment suddenly changes or the tracking error exceeds a threshold value, and the optimal track is generated by integrating energy consumption, time and safety. The system integrates high-precision sensing, self-adaptive planning and dynamic optimization, and the inspection coverage rate and the track safety under the complex shutdown attitude are remarkably improved.

The invention discloses an unmanned aerial vehicle optimal path self-adaptive planning method adopting particle swarm optimization, and relates to the field of unmanned aerial vehicle path planning, and the method comprises the steps: constructing a space constraint model of an unmanned aerial vehicle flight task; initializing a particle swarm based on the spatial constraint model; combining the path smoothness, the path threat probability and the voyage efficiency to establish a multi-target fitness function, and calculating the fitness value of each particle based on a particle swarm; hierarchical particle swarm optimization iteration is executed, in each iteration, control parameters are adaptively adjusted based on the current particle swarm distribution characteristics, and the path node positions of particles are updated; and when a convergence condition is satisfied, outputting a global optimal path as a final flight path of the unmanned aerial vehicle, and controlling the unmanned aerial vehicle to execute. According to the unmanned aerial vehicle optimal path self-adaptive planning method based on particle swarm optimization, the problems that the unmanned aerial vehicle route path optimization target is single and difficult to cooperate, and the route planning effect is poor are solved.

The invention relates to the technical field of pipeline welding automation, and discloses a pipeline multi-layer and multi-pass welding track self-adaptive planning method. The method comprises the steps that weld joint track poses, welding electrical parameters and temperature information are collected in real time, and a sliding time window data sequence is constructed; establishing an interlayer constraint model and a trajectory prediction model based on the sequence, and generating a plurality of trajectory deviation predictions through short-term recursive prediction and long-term sequence prediction; a residual error reciprocal weighted fusion strategy is combined with a welding seam forming quality evaluation function, fusion track deviation is obtained, and uncertainty is evaluated; the fusion deviation is superposed to an original planned trajectory, and a self-adaptive correction trajectory is generated through a multi-objective optimization model; and the welding robot is controlled to execute track correction and real-time feedback updating. According to the method, through dual-time scale prediction and trajectory-process parameter collaborative optimization, the problem of insufficient welding seam forming precision caused by lack of dynamic correction in traditional static planning is effectively solved, and the welding quality and efficiency are remarkably improved.

The invention relates to an intelligent management and control system for bottom mud elution operation. Comprising the steps that a polluted sediment depth feature semantic construction and evolvable model is adopted; a comprehensive sensor collects multi-dimensional information, and GNN is used for constructing a semantic map of bottom mud pollution factors; understanding the bottom mud as an evolvable pollution body to establish a response model; the bottom mud / pollution response expression model is used for follow-up control prediction; adopting elution path self-adaptive planning; taking the pollution semantic model as input, and identifying an excitation point block sensitive to disturbance of the polluted bottom mud; constructing a path diagram by using a dynamic programming algorithm; updating the response model of the polluted bottom mud, and performing path reconstruction and compression to form a workflow; a working environment perception and pollution migration prediction technology is adopted; a dynamic water body sensing system is deployed, and flow velocity, water temperature and water level changes are collected in real time; constructing a pollution migration and propagation prediction model to visualize the evolution of the pollution thermodynamic diagram along with time as a control system feedforward factor; and a multi-stage cooperative control mechanism of interference and response linkage is adopted.

The invention discloses a shape adaptive planning and control method for a deformable unmanned aerial vehicle, and the method comprises the steps: carrying out the searching based on an occupied grid map of a scene through employing a variable-size kinematics A * path planning algorithm, and obtaining an initial path; by taking the initial path as an initial condition, shape-adaptive trajectory optimization in a continuous space-time space is carried out to obtain an optimized trajectory, and in the trajectory optimization process, the mass center position and deformation parameters of the unmanned aerial vehicle are optimized at the same time; and based on the optimized trajectory, on the basis of a nonlinear model predictive controller and by combining an incremental nonlinear dynamic inverse algorithm, calculating and compensating external force disturbance and external torque disturbance caused by deformation of the unmanned aerial vehicle and a load, so as to realize shape adaptive control of the deformable unmanned aerial vehicle.

The invention relates to the field of navigation signal processing, and discloses a radiation therapy bolus dose feedback and tracking system based on image registration, the system comprises an image acquisition module, an image registration module, a bolus identification module, a dose recalculation module, a dose deviation analysis module and a feedback and adjustment module, space registration is carried out through an FBCT image acquired every day and an original plan CT, and the radiation therapy bolus dose feedback and tracking system based on image registration is obtained. The fitting state between the bolus and the skin is automatically identified, the position of an air gap is detected, and dose recalculation is carried out based on an actual structure. Through comparison with an original planned dose, the system can output a deviation index of a key dose parameter and provide visual feedback, if the deviation exceeds a set threshold value, a prompt is automatically sent out, and a radiotherapy technician and a physician are supported to carry out bolus adjustment or call an adaptive planning engine to reconstruct a treatment plan. Quantitative analysis of bolus fitting quality and closed-loop control of dose delivery consistency are realized, radiotherapy precision and safety are effectively improved, and the method is suitable for superficial radiotherapy scenes containing bolus design.

The invention relates to an APP intelligent marketing service method based on intelligent routing and multi-agent cooperation. The method comprises the following steps: receiving input information, wherein the input information comprises user active inquiry information or trigger event information generated based on user behavior monitoring; semantic analysis and intention recognition are carried out on the input information, a task planning directed acyclic graph is generated based on a recognition result, and the task planning directed acyclic graph comprises a plurality of subtask nodes and dependency relationships among the nodes; based on the task planning directed acyclic graph, the state of each functional agent and the historical performance index, executing dynamic routing so as to dispatch the plurality of sub-tasks to the corresponding functional agents; and in the execution process of the plurality of subtasks, performing dependency scheduling and state consistency management on an external tool call chain which is initiated by the functional agent and comprises a plurality of steps, and updating the shared memory associated with the user based on an execution result. By adopting the method, self-adaptive planning, robust execution and continuous optimization of marketing tasks can be realized.

The invention discloses an agent construction and development system based on a knowledge graph, and the system comprises a data collection and ontology construction module which is used for generating basic graph data; the polymorphic knowledge cell construction module is used for generating a machine-readable rule and an evidence template; the semantic mapping and deduction module is used for determining forward and reverse mapping modes and setting a consistency threshold value and a violation degree weight; the task analysis and planning module is used for outputting a feasible path and generating a plan sequence and tool arrangement; the execution and correction module is used for generating an evidence packet, constructing a forward chain, carrying out reverse reconstruction by utilizing reverse mapping, generating anti-fact candidates and writing back or backing back the anti-fact candidates; and the version and audit module is used for generating a version fingerprint for the polymorphic knowledge cellular graph which is written back and providing query and audit functions. According to the method, adaptive planning, reliable execution and traceable auditing of the intelligent agent in a dynamic task are realized by constructing polymorphic knowledge cells and cross-layer semantic mapping.

The invention provides a control method and system of a sweeping robot, and the method comprises the steps: obtaining image data, three-dimensional space data and sound data of a surrounding environment, and extracting object attribute features, space features and sound attribute features in the environment; fusing the object attribute feature, the spatial feature and the sound attribute feature to obtain an identification result; based on an identification result, executing hierarchical scene adaptive planning and executing a cleaning task by adopting a self-adaptive variational cleaning strategy; after the cleaning task is completed, second image data of the cleaned area are collected; recognizing residual stains on the ground according to the second image data and a preset cleaning effect recognition model; and if the area of the residual stain exceeds a preset area threshold value, triggering a re-cleaning program, and automatically switching a corresponding cleaning mode according to the type of the residual stain. According to the scheme, when the sweeping robot encounters the obstacles in the sweeping area, the sweeping robot can intelligently take accurate countermeasures, and an excellent sweeping effect is achieved.

The invention discloses a two-arm robot motion planning method, system and device for a strong coupling scene, and the main content is as follows: constructing a strong coupling two-arm robot closed chain system kinematic model, giving a group of mechanical arm # imgabs0 # joint configuration, and outputting a joint configuration set corresponding to another mechanical arm # imgabs1 # through the kinematic model, therefore, the planning space dimension is greatly reduced; according to a master-slave batch self-adaptive planning strategy, a mechanical arm # imgabs2 # carries out active batch self-adaptive path planning, and then a mechanical arm # imgabs3 # carries out passive batch self-adaptive path planning based on the strong-coupling double-arm closed-chain system kinematic model; and carrying out pre-motion safety check on the double-arm robot to ensure absolute safety of double-arm cooperative motion in the closed chain operation process. The problems of real-time performance and safety in a strong coupling scene are effectively solved, and reliable technical support is provided for industrial-grade double-arm cooperation.

A system (100) for adaptive real-time planning in construction projects using location and production feedback, wherein the system comprises: a data acquisition module configured to capture real-time data from construction site sensors, IoT-enabled devices, construction machinery, workforce systems, and material supply updates; a central processing engine configured to analyze deviations between planned schedules and actual site performance using adaptive planning algorithms; an intelligent feedback loop that integrates qualitative input from site managers, engineers and project managers to refine planning decisions; a visualization and dashboard module configured to display updated schedules, resource allocations, predictive alerts, and progress indicators in real time; and an integration and communication module configured to synchronize adaptive schedules with existing construction project management platforms, The system continuously updates and optimizes the schedules of construction projects to improve efficiency, resource utilization, and on-time completion.

The invention discloses a spray combustion sub-model integrated development method and equipment based on a large language model, and belongs to the technical field of engines. The method is realized by relying on a retrieval enhancement generation system and a multi-agent collaborative framework, and comprises the following steps: S1, user instruction and thesis extraction: extracting core information from related technical literatures to form a structured file according to a sub-module extension requirement proposed by a user; s2, source code analysis and comparison data generation; s3, function and interface planning: performing adaptive planning of an original model-OpenFOAM platform; s4, code generation and packaging: code conversion, dependency processing, test example generation and compilation packaging; s5, layered testing and verification graph generation; and S6, debugging and repairing: executing a positioning-repairing-regression closed-loop process through a debugging agent. According to the method, the problems that the spray combustion sub-model is difficult to migrate to the OpenFOAM simulation platform under different frameworks and the development period is long can be solved.

The invention discloses a fully-mechanized face mining method based on mining and exploring at the same time. The method is implemented according to the following steps that a data monitoring substation is arranged, and stress and micro-seismic data are received from an underground stress monitoring system; current stope stress and roof and floor conditions are obtained through stress and micro-seismic data, and a working face is guided to advance; the method comprises the following steps: establishing a transparent geologic model by using coal seam geologic information and three-dimensional space information of a working face, fusing spatial position information and working state information of fully-mechanized coal mining equipment into the transparent geologic model to obtain a mining data model, and controlling a coal mining machine by combining inertial navigation and a coal mining machine cutting curve correction model; and along with advancing of the working face, new geological information is obtained, the steps 1-3 are repeated, and the mining data model is dynamically updated. By means of the real-time dynamic monitoring and exploring while mining technology, geological exploration, data analysis and inertial navigation are integrated, sub-meter advanced high-precision exploration, geological model dynamic updating and self-adaptive planning mining are achieved, geological prediction accuracy is improved, and real-time geological navigation and stable guarantee are provided.

The invention provides a self-adaptive planning aviation fuel cell extended range power system evaluation method and system, and belongs to the technical field of power system evaluation, and the method comprises the steps: constructing a state space model of an aviation fuel cell extended range power system, building a multi-stage decision model, solving a control strategy of each stage through a self-adaptive dynamic planning algorithm, and calculating the state space model of the aviation fuel cell extended range power system. Performing difference mining on each state difference matrix, and determining an incidence relation graph of state variables and control variables in the corresponding flight stage; acquiring current state data of the aviation fuel cell extended range power system in real time, adjusting optimization parameters of a control strategy in a corresponding stage to obtain an optimal strategy in combination with a state space model and an incidence relation graph, and dynamically adjusting output power of a fuel cell and a super capacitor in combination with a power distribution strategy; and when the power output margin is lower than a safety preset threshold value, an alarm signal is triggered. And the requirements of efficient and safe operation of the aviation fuel cell range extending system are met.

The invention discloses an inspection path adaptive planning method, system and device based on laser radar point cloud and a storage medium, and relates to the technical field of robot path planning, and the method comprises the steps: collecting original three-dimensional point cloud data in an inspection environment, and carrying out the filtering processing; based on the filtered three-dimensional point cloud data, path planning is carried out in a three-dimensional point cloud space through an improved RRT * algorithm, and a minimum cost path from the starting point to the target point is generated; smoothing the path with the minimum cost to obtain a final inspection path; the method is used for autonomous inspection and rescue navigation of the robot in a complex environment, the robot can accurately avoid obstacles, rapidly plan a smooth path and stably move by processing three-dimensional point cloud data and applying an improved algorithm and the smooth path, and the task execution efficiency and the success rate are remarkably improved.

The invention discloses an unmanned aerial vehicle fan blade inspection path self-adaptive planning method and a control system, relates to the technical field of electric power inspection, and aims to solve the technical problems that a high-altitude wind power plant is complex in environment, fan blades are different in shape, and traditional inspection path planning is low in efficiency, prone to omission defects and difficult to adapt to sudden meteorological changes. Comprising the following steps: S1, acquiring three-dimensional position coordinates of all wind turbine generators in a region where a wind turbine generator needing to be inspected is located, judging feasibility of air routes among the wind turbine generators, and screening an optimal flight route; and S2, defining the orientations of any two wind turbine generators by using the optimal flight route obtained in the step S1. According to the method, deep coupling of high-altitude multi-environmental factors, blade static characteristics and paths is realized, the core problem of insufficient path adaptability of the existing method can be directly solved, the risks of power compensation misalignment and blade-path space mismatching are avoided, and basic feasibility guarantee is provided for routing inspection of the paths.

The invention provides an underwater operation path adaptive planning method and system combined with machine learning, and the method comprises the steps: employing satellite remote sensing, underwater in-situ sensing and edge computing architecture, obtaining flow fields and terrain basic data of different scales through a multi-source sensing device and technology, achieving the fusion of multi-source data through combining with an intelligent weight distribution algorithm, and achieving the adaptive planning of an underwater operation path. A high-precision real-time sensing result is output, a physical constraint and data-driven hybrid modeling framework is constructed, a spatial-temporal feature capture model is adopted to process multi-scale data, an online self-adaptive updating mechanism containing forgetting factors is designed, dynamic adaptation of the model to time-varying ocean current characteristics is achieved, simulation pre-training, on-site fine tuning and online re-planning closed-loop algorithms are constructed, and real-time ocean current sensing is achieved. The model training efficiency is improved based on reinforcement learning and transfer learning, and an optimal correction path is generated in combination with a trigger mechanism and energy consumption optimization logic.

The invention discloses a laser cutting path planning method based on reinforcement learning. The method comprises the steps that S1, a task scene model is established; s2, performing rasterization processing based on the spatial state matrix, and constructing a cutting state vector; s3, inputting the cutting state vector into a PathFormer network, extracting spatial topological features and path global semantic information, and generating high-dimensional path feature embedding; s4, constructing a multi-target reward function according to feature embedding and candidate path actions, and calculating an instant reward value; s5, training a strategy network by using an improved APPO algorithm, and updating Actor and Critic parameters to jointly optimize path length, energy consumption and hot area distribution; and S6, mapping the optimal path sequence back to the actual coordinate system to generate a control instruction, and driving the laser head to execute cutting according to the planned path. Self-adaptive planning and energy consumption balance control of the laser cutting path are achieved, and the cutting efficiency, precision and machining stability are improved.

The invention belongs to the technical field of robots, and discloses a milling force simulation and feed rate optimization method considering a robot pose dependence dynamics effect, and the method comprises the steps: firstly carrying out modal testing under different poses of a robot milling area; then, a kinetic model is established in a robot cutting area; and meanwhile, the surface of the workpiece is dynamically updated based on the dynamic sweeping track of the blade and the workpiece model, so that the calculation precision of the instantaneous cutting thickness and the cutting force is guaranteed. And finally, based on the simulated accurate cutting force, feed rate segmented self-adaptive planning under the cutting force peak value constraint is carried out, and robot curved surface part milling and machining error measurement experiments are carried out. The milling efficiency and precision of the curved surface part robot are effectively improved, and the cutting force in the machining process is more stable. And the method is of great significance to improvement of the stability and the machining performance in the robot machining process.

The invention discloses an adaptive planning method and system for a rural power distribution network containing distributed photovoltaics, and relates to the technical field of adaptive planning, and the method comprises the steps: carrying out the fault simulation based on an optimal photovoltaic access scheme, collecting fault data corresponding to a fault event generated through simulation in a fault simulation process, and carrying out the fault simulation according to the fault data; the dynamic operation risk of the power distribution network is evaluated; and based on the characteristics of the rural power distribution network and the dynamic operation risk of the power distribution network, performing multi-objective optimization, and generating a distributed photovoltaic access planning scheme. According to the invention, multi-source data is collected and preprocessed to generate a high-quality data set, and photovoltaic output and rural power distribution network characteristics are obtained, so that full-process automatic processing from data collection to power grid characteristic extraction is realized.

The invention discloses a weld defect intelligent identification and path adaptive planning system based on deep learning, and relates to the technical field of ultrasonic nondestructive testing, and the system comprises an ultrasonic data acquisition module, a defect identification module, a path planning module, a parameter adaptive regulation and control module and a result output module. The defect identification module adopts a multi-scale feature extraction network to be combined with an atlas convolution processing unit to extract deep semantic information and a global topological relation of ultrasonic features, high-precision defect identification is realized through an attention enhancement classification network, and the path planning module is used for planning a path based on a defect distribution probability graph. The self-adaptive scanning path is dynamically generated by adopting the Bayesian optimization algorithm, the detection efficiency is remarkably improved on the premise that the detection quality is guaranteed, the problems that a traditional method is insufficient in recognition accuracy and fixed and inflexible in detection path are solved, the recognition accuracy reaches 93%-96%, and the detection time is shortened by about 35%-40%.

The invention discloses a machine room resource capacity intelligent planning system and method based on multi-source data fusion, and belongs to the technical field of data center management, and the system comprises a multi-source data collection module, a resource manifold modeling module, a geodesic optimization module, a self-adaptive planning module and a verification and inspection module. The method comprises the following steps: mapping multi-dimensional resource parameters such as space, power, heat dissipation and load bearing of a machine room into a Riemannian manifold mathematical model, and constructing a resource measurement tensor representing a resource distribution density and a constraint relationship; calculating a resource allocation optimal path on the resource manifold, constructing a multi-objective function including space utilization rate, energy efficiency, heat dissipation efficiency and cost effectiveness, and generating an optimal deployment scheme of the machine room equipment; in combination with topological characteristic analysis of resource manifolds, potential resource bottlenecks are predicted, and a resource allocation scheme is dynamically adjusted; and the security and compliance of the evaluation scheme are verified through digital twinborn simulation, so that the problem of unbalanced resource allocation caused by independent planning of each system in traditional machine room planning is solved.

This invention provides an adaptive planning system and method for UAV inspection paths based on transfer learning, belonging to the field of human-machine inspection path planning technology. The system includes: constructing a vertical airflow layer structure representation model of the inspection space for inspection areas with densely packed tall structures, and outputting a set of vertical airflow layer structures for the inspection space; performing airflow layer mapping processing on the inspection path based on the set of vertical airflow layer structures, and outputting a set of airflow-adapted paths; constructing a path cost model with airflow constraints based on the set of airflow-adapted paths, and outputting a set of path costs including the total cost of the inspection path and the comprehensive cost of path segments; and performing cross-airflow layer path reconstruction based on the set of path costs and the set of vertical airflow layer structures, outputting the optimal inspection path. This accurately identifies airflow separation layers in the inspection space, achieving airflow adaptation, risk quantification, and adaptive planning of the inspection path, effectively improving the flight stability and operational safety of UAVs during inspections in areas with densely packed tall structures.

The invention relates to a self-adaptive planning method for an aircraft data link network, and the method comprises the steps: obtaining the number of micro time slots contained in all types of time slots in a communication network based on an aircraft communication link model and an aircraft motion model; based on the aircraft motion model and the micro time slot duration, obtaining a micro time slot number required by a network management information updating period of the communication network; based on the aircraft clock model and the micro time slot duration, obtaining the number of micro time slots required by a clock synchronization update period of the communication network; based on the time slot table, the number of micro time slots included in each type of time slots, the network scale of the aircraft data link network and protocol requirements, obtaining the total number of micro time slots required by each type of time slots in the communication network; arranging various types of time slots in a time slot table based on the total number of micro time slots required by various types of time slots in the communication network and the number of micro time slots required by a network management information updating period and a clock synchronization updating period; and executing the corresponding time slot task according to the time slot table. The problem that network planning is not practical and not comprehensive is effectively solved.

The invention discloses a whole-process data perception and comprehensive evaluation method and system for intelligent homework accompanying, and belongs to the technical field of intelligent education and human-computer interaction. The method comprises the following steps: before homework, generating a dynamic homework plan based on a homework list, student historical data and a real-time state; during operation, academic, behavior and emotion data are collected through a multi-modal sensor and are processed under an end-cloud architecture; in the writing process, handwriting recognition is combined with a knowledge graph to realize real-time discovery and attribution of wrong questions; after operation, a comprehensive evaluation report is generated based on the multi-dimensional evaluation model, feedback is output through a natural language generation module, and the report is stored after being subjected to credible evidence storage processing. The system realizes objective monitoring and personalized evaluation of the whole process of student homework through cooperation of dynamic adaptive planning, real-time error attribution, multi-modal perception fusion and block chain evidence storage, and has the advantages of improving accompanying quality, enhancing report credibility and facilitating long-term tracking.

The invention relates to a method for wirelessly updating software in a motor vehicle, in which a communication connection with an external server is established by means of a first detection device in order to detect software updates, and in which software updates received by means of a processing device are installed in the motor vehicle, wherein operating states of the motor vehicle are checked by means of a control logic before a software update is carried out. wherein semantic information about the software updates is processed by means of a local language model device and evaluated according to predefined / specified rules, in particular security and policy rules, and adaptive planning and prioritization of the updates is carried out by means of the processing device depending on vehicle states and / or operational conditions. The invention further relates to an update system (10).

The invention provides a lightweight satellite-borne satellite group adaptive planning method based on Transform-DRL, and belongs to the field of satellite autonomous planning. According to the method, firstly, environment input is carried out, target events and feasible satellites are screened, feature construction is carried out, then, generated hidden representations are projected into a unified potential space through a full connection layer, context sensing representations are obtained, and then, context sensing is carried out on the basis of the representations. The strategy network scores feasible event-satellite actions and generates probability distribution, actions are selected to be executed in combination with action masks, Transform and strategy parameters are updated end to end through an Actor-Critic mechanism according to rewards after execution, and satellite group autonomous task planning is achieved. The method has the characteristics of high efficiency of arranging different types of events and satellites, high autonomy and the like, and is suitable for flexible and autonomous satellite group task planning.

The application provides a UAV recovery path adaptive planning method and system based on air-ground cooperation, relates to the technical field of robot motion planning, and comprises the following steps: constructing a three-dimensional grid map of a task environment, acquiring the positions of a UAV and an unmanned vehicle and the maximum flight distance of the UAV; determining the responsibility distribution of the UAV and the unmanned vehicle in a recovery task based on the positions of the UAV and the unmanned vehicle and the maximum flight distance of the UAV, and obtaining an optimal UAV recovery scheme; selecting a corresponding path planning mode according to the optimal UAV recovery scheme, and determining the starting point, the ending point and the dimension of the search space of path planning based on the positions of the UAV and the unmanned vehicle; executing a path planning algorithm according to the selected path planning mode, and generating a final recovery path; and through air-ground cooperative decision and cross-dimension bidirectional joint path planning algorithm, the application realizes safe and efficient recovery of the UAV under the constraint of electric quantity, and significantly improves the task success rate and the system cooperation efficiency.

The invention discloses a multi-robot uncertainty perception adaptive dynamic task planning method and system. The system comprises a dynamic target trajectory estimation module, a task analysis and decomposition module, a conformal prediction-based Monte Carlo tree search task distribution module and a rolling time domain adaptive adjustment module. For linear sequential logic tasks triggered offline and online in a heterogeneous multi-robot system, including dynamic tasks associated with dynamic targets in an environment, online generation of a task plan is realized through an uncertainty perception adaptive planning method, so that the average response time of the tasks is minimized. By adopting the technical scheme provided by the invention, collaborative task planning and execution can be efficiently completed in a complex environment with a dynamic target and a complex time sequence constraint task.

The invention discloses a policy sensitivity-driven multi-town industry deduction parameter adaptive planning system. The system comprises a data acquisition module, a deduction calculation module, a policy sensitivity analysis module, a multi-town industry linkage deduction module, a parameter adaptive correction module and a deduction result verification module. The policy sensitivity analysis module extracts policy indexes to generate influence weights, the multi-town industry linkage deduction module constructs an incidence matrix to calculate overflow effect coefficients, the parameter adaptive correction module dynamically adjusts deduction parameters, and the deduction result verification module outputs verification errors; the system solves the problems that existing deduction parameters are fixed and do not adapt to policy and industry linkage, and improves the accuracy and dynamic adaptability of multi-town industry deduction.