808 results about "Autonomous control" patented technology

Disclosed in the present invention are a multi-modal shared teleoperation system and method for a three-arm space robot. The system at least comprises a master-side teleoperation system, a communication module and a slave-side robot system, wherein the master-side teleoperation system at least comprises two force feedback hand controllers, a microphone array and upper computer software, and the slave-side robot system comprises two operating arms each equipped with a gripper at the end, an observation arm having a binocular camera mounted at the end, a vision unit, a force sensor and lower computer software. The method comprises: an operator controlling two operating arms of an extravehicular robot to execute a task, and controlling an observation arm to acquire a better local field of view. In the method, a multi-modal teleoperation method comprising pose control, voice control and force control is fused with autonomous control of a robot by means of a shared control algorithm, and thus, human-robot collaborative control over the position, orientation and contact force of a robotic arm can be realized on the basis of the requirements of the operator, and the robot autonomously executes other relatively simple tasks, thereby reducing the operation burden of operators, and improving the control efficiency.

A multimodal shared telerobotic system and method for a three-arm space robot, the system at least includes a local-site system, a communication module, and a remote-site system, where the local-site system includes two force-feedback haptic devices for left and right hands, a microphone array, and upper computer software; the remote-site system includes two robotic arms provided with end-effectors, an observation arm with a stereo camera installed at an end thereof, two force sensors, a vision unit and lower computer software; an operator can control the two robotic arms of the robot outside a cabin for performing operations, and control the observation arm to obtain a better local view; and a multimodal telerobotic control method of pose control, voice control, and force control is integrated with the robot's autonomous control through a shared control algorithm.

The invention discloses a micro-grid dynamic coordination control method and system for distributed energy, and relates to the technical field of micro-grid energy management. The method comprises the steps of 1, collecting multi-source micro-grid data in real time, performing edge calculation and data preprocessing operation, and performing early judgment of an island mode; 2, converging the structure and state of each micro-grid, dynamically constructing and updating a micro-grid topological graph, analyzing the structure change and health condition of the micro-grid topological graph, and evaluating the comprehensive risk of micro-grid nodes; 3, calculating the actual distributable power of each type of loads, and carrying out autonomous control and elastic mode switching; and step 4, on the basis of the actual distributable power of each type of loads, evaluating the collaborative energy scheduling capability of the micro-grid in real time, performing role identification and implementing an optimization strategy. The problem of island emergency scheduling response lag caused by sudden failure of a main network due to some extreme events along with continuous expansion of the access scale of distributed energy and a micro-grid is solved.

The invention relates to the technical field of unmanned aerial vehicle autonomous control, and discloses an unmanned aerial vehicle obstacle avoidance control method and system based on computer vision, and the method comprises the steps: collecting the multi-view image data of a flight environment in real time through a multi-view camera, and carrying out the preprocessing; using an improved YOLOv7 network to identify obstacles in the preprocessed image, and extracting position, size and motion information of the obstacles; generating a three-dimensional environment map and a plurality of candidate obstacle avoidance paths in combination with the flight parameters of the unmanned aerial vehicle and the extracted obstacle information; an optimal path is screened based on a dynamic safety evaluation model, and the attitude and power output of the unmanned aerial vehicle are adjusted in real time to complete obstacle avoidance; an obstacle avoidance effect is verified by using an optical flow method and depth information, and path planning is dynamically corrected. According to the method, the dynamic safety evaluation model is introduced, multi-dimensional factors are comprehensively considered, the safety of each path is dynamically determined, and it is ensured that the flight path of the unmanned aerial vehicle can be timely and accurately modified and optimized in a dynamic complex environment.

The invention discloses a double-arm robot autonomous control system and method based on teleoperation and visual features. The system comprises a teleoperation acquisition module, a multi-view visual perception module, a data synchronization and demonstration acquisition module, a strategy model training module, an autonomous strategy execution module, a track deviation detection and takeover module and a hybrid control interface module. Human demonstration is completed through teleoperation, multi-modal information of images, tracks, clamping jaws and muscle activation is collected, perception features are fused by adopting multi-view space-time alignment and a cross-view attention mechanism, strategy learning is completed in combination with an end-to-end large model, and in the autonomous operation stage, the multi-view space-time alignment and the cross-view attention mechanism are combined with the end-to-end large model. The risk of current operation is predicted and evaluated through track deviation detection and collision probability, the autonomous control proportion is dynamically adjusted, manual intervention is allowed when necessary, the safety and stability of the whole system are improved, the robot control mode of seamless switching between man-machine cooperation and autonomous and teleoperation is achieved, and the method is suitable for object control tasks in complex and highly variable environments.

The invention relates to the field of power distribution networks, in particular to a power distribution network voltage collaborative autonomous method and system based on dynamic partition. The method comprises the following steps: acquiring electrical measurement data and network topology parameters of distributed nodes of a power distribution network, and generating a characteristic state set representing the operation state of a system; performing dynamic subarea division based on node voltage coupling strength and power balance constraint to obtain a dynamic subarea set with an autonomous boundary; each partition control main body independently solves a voltage regulation objective function of the partition according to an autonomous boundary, and generates a partition autonomous control strategy; and boundary interactive iterative coordination is carried out between adjacent partitions, and a global optimal voltage cooperative control instruction is generated and executed. According to the method, the problems that partition division is not matched with the operation state, and partition collaboration is insufficient are solved, unification of partition autonomy and global optimization is achieved, and the real-time performance and accuracy of voltage regulation and control of the power distribution network are remarkably improved.

The invention relates to the technical field of intelligent equipment autonomous control, and discloses an AIGA-driven intelligent equipment autonomous control and feedback adjustment method, which comprises the following steps of S1, collecting equipment body state parameters and external environment data in real time through a multi-mode sensor array; s2, combining the collected data with a preset user instruction and a real-time environment semantic analysis result; s3, disassembling the task target into a continuous action instruction set; s4, executing the action instruction set through the layered real-time control architecture; s5, monitoring an action execution effect based on the multi-modal sensor array; and S6, analyzing the relevance between the evaluation result and the action instruction through a causal inference engine. According to the method, an equipment action execution result is fed back to an intention generation layer in real time, a deviation source is positioned through a causal inference engine, a control strategy is dynamically adjusted, closed-loop iteration from one-way instruction execution to perception-decision-execution-verification is achieved, and the effect of self-adaptability in a dynamic scene is achieved.

The invention provides an anti-condensation temperature and humidity regulation and control system and method for remote deep learning prediction aided decision making, and the method is characterized in that a field controller is connected with a temperature and humidity collection device, obtains the environment temperature and humidity, calculates the dew point temperature, obtains the surface temperature of a protected part, and starts and stops a heating and / or dehumidification device by comparing the difference between the two values with a preset threshold value; the temperature and humidity acquisition device acquires field environment temperature and humidity data for the field controller to calculate the dew point temperature, and the temperature and humidity acquisition device is also used for acquiring the surface temperature of the protected part; the heating device is used for raising environment temperature; the dehumidification device is used for reducing the environment humidity; the communication module is used for data transmission between the field controller and the remote prediction terminal, sending field data and receiving prediction information; the remote prediction terminal obtains field data through the communication module; an anti-condensation system structure combining local autonomous control and remote prediction assistance is established, and redundancy fault-tolerant capability is achieved; even if the remote prediction function fails, the field control can still operate independently and reliably.

The invention discloses a satellite formation autonomous control method based on relative motion fitting, belongs to the technical field of spacecraft control, and aims to solve the problem that a traditional formation control method cannot meet formation control requirements in an environment with navigation signal deficiency. The method comprises the following steps: step 1, when a main satellite passes through an ascending node, performing relative motion fitting by utilizing inter-satellite spacing and direction of a plurality of discretely distributed sub-satellites relative to the main satellite observed in a previous orbital period so as to obtain coefficients of relative motion functions of the sub-satellites; step 2, obtaining orbit parameter deviation of the child satellites relative to the primary satellite according to the coefficient of the relative motion function of the child satellites; step 3, acquiring a control vector and a control duration required by the formation adjustment of the child satellites according to the orbit parameter deviation; and step 4, each sub-satellite performs autonomous control according to the control vector and the control duration obtained in the step 3. The method is used for satellite formation autonomous control.

The invention provides a high-precision topographic mapping and three-dimensional modeling system based on an unmanned aerial vehicle, and the system comprises an unmanned aerial vehicle cooperation module which is used for deploying a multi-source sensor and a sensor electronic interface on the unmanned aerial vehicle, and building a distributed network of the unmanned aerial vehicle; the real-time dynamic positioning module is used for acquiring unmanned aerial vehicle positioning data and an initial target terrain map; the autonomous control module is used for generating a flight path, performing dynamic adjustment, constructing an autonomous flight control model and outputting a flight control instruction; the data quality enhancement module is used for performing parameter adjustment on the real-time data and performing space and signal level combined processing on the real-time data so as to enhance the data quality; and the terrain model optimization module is used for processing the laser radar point cloud data so as to construct a three-dimensional terrain model post-processing module, and carrying out data visual display and flight suggestion generation. According to the method, the positioning and modeling precision is greatly improved, efficient surveying and mapping are achieved, the single-point fault risk is reduced, and it is guaranteed that tasks can be completed in a high-safety, high-precision and intelligent mode.

The invention relates to the technical field of tunnel engineering safety monitoring, in particular to an autonomous controllable three-dimensional tunnel gushing analysis method and system. The method comprises the following steps: collecting multi-source heterogeneous geological, hydrological and construction data, fusing to obtain multi-source heterogeneous data, and constructing a dynamically updated three-dimensional geological-construction coupling digital twinborn model after alignment coding; carrying out multi-scale physical-AI hybrid modeling, correcting real-time data, carrying out water gushing evolution rolling prediction, and outputting prediction data; a three-dimensional visual platform is constructed, and multi-level linkage early warning is started based on a risk threshold value; the system comprises a data fusion module, a water gushing evolution rolling prediction module and a multi-stage linkage early warning module. By fusing geological data, hydrological monitoring data and construction parameters and combining three-dimensional visual rendering and deep learning fluid simulation technologies, the requirements for rapid early warning and timely decision making of water burst disasters in the tunnel construction process are met, and intelligent support is provided for engineering disaster prevention decision making.

The invention discloses a bridge ship collision early warning system based on artificial intelligence, and relates to the field of intelligent traffic infrastructure safety protection. The method is used for solving the problems of difficulty in multi-source data fusion and low risk identification accuracy in a complex water area. The method comprises the following steps: firstly, uniformly mapping a radar point cloud, an AIS signal and a visual trajectory to a coordinate system taking a pier as a center through a Lie group transformation algorithm, and constructing a ship motion state tensor; then, ship behavior characteristics are extracted through a space-time diagram convolutional network, and intention probability distribution and behavior deviation degree are output; thirdly, an orthogonal constraint variational auto-encoder is adopted to decouple the autonomous control behavior and the environment disturbance factor, and a collision risk quantized value is generated according to the norm ratio of the autonomous control behavior and the environment disturbance factor; and finally, constructing a dynamic alarm threshold value according to the behavior deviation degree and the disturbance characteristics, realizing graded early warning, and driving a behavior pattern library to update through a feedback mechanism to form a self-adaptive closed-loop early warning system.

Systems and techniques are described for implementing autonomous control of powered earth-moving vehicles, including to automatically control movement of a vehicle's component parts on a job site to perform tasks. The techniques may include using an MPC-based Control System to perform a cycle of training and deployment of a predictive model specific to a particular earth-moving vehicle to control that vehicle's autonomous operations, and to further using resulting data in additional manners—such a cycle may include using a data gathering module on the vehicle to gather actual operational data of the vehicle during manual control of the vehicle on job site(s) by human operator(s) during performance of task(s), generating a 3D site map modeling the vehicle's surroundings, training a Model Predictive Control (MPC) model based on the actual operational data and 3D site map, and deploying the trained model to the vehicle for use in autonomous operations.

A symbolic neuroadaptive control system is disclosed for real-time arbitration, consent, and ethical modulation of artificial intelligence agents operating in wearable computing environments. The system integrates multimodal biometric telemetry—including high-resolution EEG signals—with a symbolic kernel that performs logic-driven arbitration over cognitive, emotional, and ethical states. Using Coq-verified invariants and zero-knowledge biometric consent tokens, the system constructs a deterministic symbolic execution graph, gating AI outputs based on internal user states such as trauma, stress, or intentionality. Unlike conventional black-box BCI models, the invention routes EEG-inferred affective-symbolic tokens through a formal ethics layer that enforces real-time interrupt control, utility bounding, and trust verification. The kernel enables AGI systems to defer or modify behavior based on user-state alignment, granting sovereign agency over all downstream actions. This neuro-symbolic architecture redefines the interface between human cognition and intelligent machines, enabling emotionally conscious, morally verifiable, and symbolically transparent AI governance in dynamic, high-stakes contexts.The present invention relates to artificial intelligence and neurotechnology, specifically to a real-time, neuro-symbolic operating system kernel that converts electroencephalography (EEG) signals into structured symbolic data for use in emotional cognition, ethical prioritization, autonomous agent dispatch, and real-time telecommunications routing. The invention bridges brain-computer interface (BCI) inputs with symbolic AI architectures to enable ethically aligned machine response during cognitively or emotionally intense events.

The invention discloses an ocean wind power underwater noise monitoring method and system, and belongs to the technical field of ocean environment monitoring, artificial intelligence and autonomous systems.The ocean wind power underwater noise monitoring method comprises the steps that a digital twinborn model fusing multi-mode perception is constructed; deducing future states of the system and the environment based on a digital twinborn model to generate a predictive state sequence; solving and generating a cooperative control strategy according to a joint optimization target of data quality and energy consumption; and analyzing the cooperative control strategy to synchronously regulate and control the physical system. According to the method, a digital twinborn driven cognitive decision and autonomous control architecture is adopted, a high-fidelity digital twinborn body is constructed to carry out prospective and uncertainty deduction on a physical system and a marine environment, and a closed-loop decision is carried out by taking risk-income optimization as a principle; the monitoring system can have long-term, autonomous and online self-improvement and risk avoidance capabilities, and the reliability of monitoring data in a complex marine environment and the full-life-cycle autonomous operation level of the system are remarkably improved.

The invention relates to the technical field of unmanned aerial vehicle autonomous control, and discloses a power transmission line unmanned aerial vehicle autonomous inspection path planning method and a quality inspection system, and the method comprises the following steps: obtaining or constructing and dynamically evolving a cognitive digital twin containing geometric, semantic and uncertainty information; based on the first task intention, aiming at reducing the uncertainty of the cognitive digital twinning, generating a first flight path by optimizing information gain; controlling the unmanned aerial vehicle to fly along the first flight path, and performing in-service quality inspection on the acquired data to obtain a quantized target component defect suspected degree; and when the defect suspected degree meets a preset risk triggering condition, dynamically generating a second task intention with a higher priority, and generating a second flight path for fine detailed investigation based on the intention so as to replace or modify the first flight path. According to the invention, the unmanned aerial vehicle is converted into an active diagnosis agent from a passive path executor, and the autonomy, reliability and efficiency of routing inspection are significantly improved.

Systems and techniques are described for implementing autonomous control of earth-moving construction and / or mining vehicles, including to automatically determine and control autonomous movement of part or all of one or more such vehicles (e.g., a vehicle's arm(s) and / or attachment(s), such as a digging bucket, claw, hammer, blade, etc.) to move materials or perform other actions in a manner that is based at least in part on data from simulated operation of the vehicle(s). For example, the systems / techniques may include using data from simulated operation of the earth-moving vehicle(s) in various manners, such as for use in training one or more machine learning models that are used in implementing the autonomous operations, determining optimal or otherwise preferred hardware component configurations to use, determining optimal or otherwise preferred implementation plans to use for one or more tasks and / or multi-task jobs, enabling user what-if experimentation activities, etc.

The invention discloses a robot image-free visual target docking method and system based on multi-modal perception, and the method comprises the steps: carrying out the recognition calculation of a preset target in the image data of the environment in front of a robot through a target detection model YOLOv4-tiny, and constructing a robot control feedback quantity; radial distance information of an object in the environment is obtained, a scanning range is divided through a regional strategy, straight line fitting calculation is conducted, and a deviation evaluation value of the robot relative to the yaw angle is constructed; and the robot accumulative mileage is obtained, finite-state machine hierarchical decision making and mistaken stop prevention judgment are conducted in combination with the robot control feedback quantity and the robot relative yaw angle deviation evaluation value, and robot graph-free visual target docking is achieved. According to the invention, full-process autonomous control of the robot from target discovery, navigation on the way, obstacle avoidance to end fine alignment can be realized. The robot graph-free visual target docking method and system based on multi-modal perception can be widely applied to the technical field of graph-free navigation.

The invention relates to the field of intelligent unmanned aerial vehicle autonomous control and decision making, in particular to an unmanned aerial vehicle trajectory planning method based on a noise dual-depth Q network, which comprises the following steps: acquiring unmanned aerial vehicle sensor data; establishing a forest fire model according to unmanned aerial vehicle sensor data; establishing an unmanned aerial vehicle constraint condition and an optimization function according to the forest fire model, and converting the unmanned aerial vehicle constraint condition and the optimization function into a partially observable Markov decision process; solving the partial observable Markov decision process by adopting a noise double-depth Q network to obtain an optimal unmanned aerial vehicle path planning strategy; according to the invention, the node areas are taken as decision objects, and value grading is carried out on different node areas, so that the decision is more in line with the reality; a noise bias item is introduced into a neural network weight to balance learning stability and exploration performance, so that the network can dynamically adapt to exploration behaviors in different environments; and a trajectory smoothness constraint is designed to ensure that the flight path is continuous, and the success rate of unmanned aerial vehicle trajectory planning is further improved.

The invention relates to the technical field of aerostats, solves the technical problem that a traditional CD-ROM device control design method is large in application range limitation, and particularly relates to a control method of a floating device and an autonomously-moving floating device.The control method comprises the steps that an independent air chamber is filled with low-density air, and the floating device autonomously floats in air; and establishing a control equation for controlling the autonomous movement of the floating device by controlling the illumination intensity, placing the floating device floating in the air in the illumination area, and autonomously controlling the floating device to advance according to the preset direction based on the control equation. The optical drive control system is simplified by utilizing the deformation characteristic of the liquid crystal elastomer, so that the light weight of the floating device is realized, fuel and a controller do not need to be carried, and long-time autonomous flight can be realized by utilizing photo-thermal energy so as to adapt to complex and changeable application scenes.

The invention discloses a power distribution control method and device for an optical storage DC flexible power distribution system, and relates to the technical field of power distribution control methods, and the method comprises the steps: determining a power consumption path of each power distribution region based on a power load and a photovoltaic power generation path of each power distribution region, and an energy storage path corresponding to the optical storage DC flexible power distribution system; and the power distribution balance event of each power distribution area is determined according to each power consumption path, the power distribution level of each power distribution area and the power distribution control relationship among the power distribution areas, so that the accuracy of the power distribution balance event of each power distribution area is improved. Therefore, the dynamic restoration event of the power distribution area is determined based on the autonomous management and control system and the abnormal power distribution position of the power distribution area, and the flexible regulation and control event of the optical storage direct-current flexible power distribution system is determined based on each dynamic restoration event, the working process of the optical storage direct-current flexible power distribution system and the flexible management and control path. And the autonomous flexible regulation and control effect of the optical storage direct-current flexible power distribution system is ensured.

The invention relates to a man-machine cooperation fabricated construction management and control system and method based on a BIM and a Unity model.The BIM is integrated into a man-machine cooperation construction workflow through an interactive closed-loop digital twin framework, the closed-loop digital twin framework comprises a model building module, a man-machine interaction module, a middle layer module and a data collection module, the model building module is used for building a BIM model for the prefabricated part; the man-machine interaction module realizes manual remote control through a graphical user interface, issues an instruction to the robot, intervenes and supervises the construction process, and transmits the instruction to the middle layer module through a programming language; the middle layer module is provided with a data processing module, a machine autonomous control module and a decision information integration module; and the data is transmitted to the BIM through the data processing module to update the BIM model so as to reflect the change between the design construction state and the actual construction state. The method has the advantages that the participation degree of the building robot in site construction work is improved, and a solution is provided for intelligent construction of the fabricated building.

The invention discloses an AI multi-agent layered hierarchical emergency response system supporting an elastic power grid, and relates to the technical field of substation power response, the AI multi-agent layered hierarchical emergency response system comprises a global situation awareness module, a regional autonomous control module and an equipment toughness execution module, the global situation awareness module integrates multi-source disaster monitoring information, establishes a disaster chain deduction model, and sends the disaster chain deduction model to the regional autonomous control module; quantifying regional disaster intensity and generating a risk map; the regional autonomous control module extracts a high-risk region to divide a balanced island, realizes second-level splitting and black start through an intelligent agent, and constructs an autonomous stability coefficient to evaluate the stability of the island; and the equipment toughness execution module identifies a potential fault area, drives an intelligent agent to dynamically reconstruct a power grid topology, links distributed energy to perform differential energy supplementation according to a load gap, and calculates a recovery speed coefficient to judge the core load recovery quality. The system improves disaster pre-judgment precision and emergency response efficiency, ensures reliable power supply of medical and industrial core loads, and enhances disaster resistance elasticity of a power grid.

Provided herein is a control system and methods thereof for controlling operation of a robot. The control system comprises: a robot, including a plurality of sensors wherein each generating a stream of raw sensor data having a data type, size, and frequency, and a plurality of actuators cause movement of the robot; an autonomous control subsystem configured to receive the sensor data and output autonomous actuator data; and a teleoperation control subsystem configured to receive the sensor data, transmit the sensor data to a human operator, and output teleoperation actuator control signals, wherein the autonomous control subsystem and the teleoperation control subsystem receive, from the robot, sensor data having the same data type, size, and frequency, and wherein the autonomous actuator data and the teleoperation actuator data have the same data type, size, and frequency; and a control-determining subsystem configured to switch between autonomous and teleoperation control.

A system and method includes an autonomous agent having a communication interface that enables the autonomous agent to communicate with a plurality of infrastructure sensing devices; a plurality of distinct health monitors that monitor distinct operational aspects of the autonomous agent; an autonomous state machine that computes a plurality of allowed operating states of the autonomous agent based on inputs from the plurality of distinct health monitors; a plurality of distinct autonomous controllers that generate a plurality of distinct autonomous control instructions; and an arbiter of autonomous control instructions that: collects, as a first input, the plurality of autonomous control instructions generated by each of the plurality of distinct autonomous controllers; collects, as a second input, data relating to the plurality of allowed operating state of the autonomous agent; and selectively enables only a subset of the autonomous control instructions to pass to driving components of the autonomous agent.

The invention relates to the technical field of satellite attitude control, in particular to a satellite-borne laser semi-autonomous pointing control method, electronic equipment and a storage medium. The method is completed by cooperation of a ground system and an on-satellite system, the ground system calculates a top target passing moment T * in advance, generates a unified laser pointing control instruction and injects the instruction into a satellite; and the satellite-borne system receives and analyzes the instruction, obtains parameters such as T * and beam selection, and then autonomously controls a specified load for work preparation. And the satellite-borne system autonomously calculates the optimal moment T1 and the target attitude when passing through the calibration field through high-precision orbit extrapolation based on the latest navigation data, finally autonomously executes attitude maneuver and laser pointing tasks, and autonomously returns after the tasks are completed. Instructions in a uniform format are generated and injected from the ground, ground operation is greatly simplified, efficient cooperation of ground decision triggering and on-satellite autonomous execution is achieved, pointing errors caused by orbit extrapolation are greatly reduced, the pointing precision and the task success rate are improved, and universality is good.

The invention provides a micro-grid control method based on edge side AI control equipment and a program product, and relates to the field of power supply and consumption system control. The micro-grid control method comprises the following steps: deploying a lightweight large model on edge side control equipment, wherein the lightweight large model is obtained through compression based on a pre-selected universal large model; micro-grid operation demand information input in a natural language form is acquired by the lightweight large model, and a control target is analyzed from the micro-grid operation demand information; generating a control strategy according to the control target; and controlling the operation state of the micro-grid according to the control strategy. According to the scheme of the invention, the lightweight large model is deployed at the edge side control equipment, the microgrid operation demand information is obtained through a natural language, the convenience and flexibility of control are improved, and the control demand is better met. And a light-weight large model accurately generates a control target and a strategy, so that more accurate operation control is realized, the adaptive capability is enhanced, and intelligent autonomous control is realized.

The invention discloses a mixed cooling system multi-target parallel control method based on virtual-real migration. The method comprises the following steps: coupling characteristic analysis and cooperative control logic construction; a data-driven multi-step rapid prediction model is constructed and corrected online; and virtual-real migration feedback and multi-target parallel control optimization are carried out. Multi-step prediction is realized by constructing a multi-parameter coupled agent model and fusing an LSTM technology; and a virtual-real double-closed-loop collaborative optimization mechanism is constructed under an ACP parallel control framework, so that real-time self-adaption and multi-target rapid adjustment of control logic are realized. The invention further discloses a mixed cooling system multi-target parallel control system based on virtual-real migration. Compared with a traditional method, the technology breaks through the modeling bottleneck and realizes rapid prediction; virtual-real parallel control is initiated, and strong anti-interference and high maneuverability are achieved; carrying out online multi-target collaborative optimization; intelligent cooperative execution control; the application platform is efficiently verified; the dynamic performance is obviously improved; the comprehensive performance is excellent, and the system operation stability and the autonomous control level can be remarkably improved.

A distributed spatio-temporal joint trajectory planning method for an intelligent agent cluster relates to the technical field of robot autonomous control, and comprises the following steps: planning the moving trajectory of each intelligent agent; collision conflict information between any intelligent agent and other intelligent agents in the cluster is detected in sequence, and the collision conflict information is sent to the other intelligent agents through network broadcasting; any agent generates a conflict graph after receiving the collision conflict information; based on the conflict graph, an approximate minimum vertex coverage algorithm is adopted to solve the minimum subset of the agents needing to re-plan the trajectory; re-planning the moving trajectory of the agents in the minimum agent subset at the same time; repeating the steps of collision conflict information detection, conflict graph generation, minimum agent subset construction and moving trajectory re-planning until the number of detected conflict information is zero, and determining the final moving trajectory of each agent; the method is used for solving the problems that traditional space-time coupling processing is poor, expandability is poor, dependence on a front-end path is high, and multi-constraint processing is complex.

The invention provides a shield tunneling machine earth pressure balance autonomous control method based on warm start DDPG, and relates to the technical field of shield tunneling machines. Comprising data warm start and reinforcement learning training; warm start is carried out on the Actor network based on a large amount of construction data, and hidden key features and rules in the data are learned; on the basis of warm start, a deep reinforcement learning method is introduced, a control strategy is continuously optimized through interaction with an actual construction environment, and finally intelligent decision-making of earth pressure balance of the shield tunneling machine is achieved. Through data pre-training, the Actor network can preliminarily adapt to a complex construction environment, the number of trial and error times is reduced, and the invalid trial and error cost at the initial stage of intelligent agent training is remarkably reduced. And reinforcement learning training forms a closed-loop control chain of state perception-decision optimization-execution feedback through real-time interaction with a dynamic construction environment, so that not only is gradual fine adjustment of a control strategy in the tunneling process realized, but also the decision response speed and precision are improved, and finally, intelligent decision making of earth pressure balance of the shield tunneling machine is realized.