66 results about "Decision networks" patented technology

This application relates to the field of logistics robot technology, and in particular to a logistics robot control method and system based on online transfer learning. It includes: collecting environmental state data through the logistics robot's sensor array, generating a state vector based on the environmental state data; inputting the state vector in parallel to two processing channels of a preset control algorithm, and outputting motion control commands for the logistics robot; updating the state vector based on the execution results of the motion control commands, generating learning signal parameters, and setting an optimization learning strategy for the control algorithm based on the learning signal parameters; and achieving functional decoupling of high-level decision-making and rapid adaptation by constructing a parallel dual-pathway architecture of a brain-decision network and a cerebellum-adaptive network. The brain-decision network outputs basic motion commands based on cross-environment task planning and strategy transfer; the cerebellum-adaptive network focuses on handling dynamic disturbances in the logistics scenario, providing real-time fine-tuning.

This invention discloses a method and system for detecting foreign objects in food based on dynamic routing with information entropy and graph convolution, belonging to the field of food detection technology. This invention generates a corresponding two-dimensional information entropy feature map by calculating the discrete data of a multi-scale basic feature tensor. This map is then input into a routing gating network to generate a spatial routing mask. The spatial routing mask is used to partition the multi-scale basic feature tensor into high-entropy and low-entropy feature streams, which are then subjected to topological and convolutional processing to generate first and second discriminative features. These features are then fused with the spatial routing mask to generate a full-graph fusion feature tensor, which is then input into an evidence decision network. The network outputs category judgment confidence and cognitive uncertainty, which are then compared to determine whether to generate a physical interception command and output a foreign object rejection result. This reduces the false detection rate of foreign objects in food detection and solves the problem of increased false detection rates in existing technologies.

The application discloses an intelligent decision method and system for warehouse operation process optimization, and relates to the technical field of intelligent warehouse management, which comprises the following steps: collecting warehouse multi-source heterogeneous data, and constructing a full-factor feature dataset; constructing a warehouse global coupling graph model, and calculating a global coupling weight matrix through a double-layer coupling mechanism of direct coupling attention and indirect chain coupling attention; constructing a coupling perception decision network, generating initial decisions for each operation link, and simultaneously calculating dynamic coupling constraint thresholds; performing global collaborative iterative optimization according to the global coupling weight matrix and the coupling constraint thresholds; and real-time monitoring of warehouse abnormal events triggers local re-optimization, and adjusting the global collaborative decision to obtain the final decision. The application aims to solve the problem that in the existing warehouse decision, each operation link is independently modeled and optimized, and there is a lack of global collaborative consideration of the strong coupling correlation among multiple links, which is easy to fall into local optimization.

The present application provides a corn optimal seeding rate decision-making method based on multi-source field information fusion, comprising the following steps: obtaining multi-source data of the target field, respectively constructing yield prediction model data set and optimal seeding rate true value data set, and carrying out data preprocessing; constructing an end-to-end optimal seeding rate decision network, the decision network comprising a feature coding module, a double-dimension weight learning module and a gated weighted fusion module; completing feature embedding and global context modeling through the feature coding module, completing adaptive contribution modeling of two types of dimension representation through the double-dimension weight learning module, and completing multi-dimensional information fusion and adaptive weighting of multi-path candidate decision through the gated weighted fusion module, and finally outputting the optimal seeding rate prediction value; using a yield-guided step-by-step training architecture to train the decision network, obtaining target multi-source field information of the to-be-seeded plot, inputting the trained optimal seeding rate decision model, and outputting the optimal corn seeding rate of the corresponding plot.

The application discloses a kind of wind power variable pitch system control parameter self-adapting setting method and system, it is constructed as dynamic graph to wind farm, and the wake influence between units is quantified by dynamic adjacency matrix.Meanwhile, macroscopic dispatching instruction of power grid is encoded as context vector.For any wind turbine in the field, first observe the machine data, and quantify its topological role based on dynamic adjacency matrix.The topological role is used to generate context modulation gate to differentiate adjustment global context vector, so that it adapts to the current wind turbine role.Subsequently, graph neural network fuses the local state of the wind turbine, dynamic adjacency matrix and personalized context modulated by role, to generate enhanced state vector.Finally, the enhanced state vector is input into the cooperative decision network, and is parsed into optimal PID parameter increment to update local PID parameter.The scheme makes each wind turbine execute control strategy matched with its topological role and global target through this distributed intelligent decision, to optimize the performance of the whole field.

The application discloses a kind of synergy performance driven manned aircraft / unmanned aircraft cooperative decision-making methods, first construct time-varying weighted cooperative task network, manned aircraft, unmanned aircraft, task node and risk node are uniformly modeled, and construct the cooperative performance index of fusion network efficiency and robustness retention.Furthermore, a structured distributed controller is designed, each unmanned aircraft outputs a non-negative trade-off coefficient for the three types of behavior items of formation keeping, task guidance and risk avoidance according to local abstract variable, and synthesizes continuous control input.The cooperative performance increment is embedded in the strategy optimization reward, and through the closed-loop iteration of control decision, network update-performance calculation-increment feedback, the distributed strategy is continuously optimized in the direction of improving cooperative performance.The manned aircraft realizes the consistency of target and execution under stage switching by modulating the efficiency-robustness preference, node importance and link task correlation in the performance index, and updating the reference guidance signal.

This invention provides a robotic satellite assembly method based on multimodal reinforcement learning, belonging to the field of robotics. The method comprises a multi-degree-of-freedom spatial robotic arm system, a force perception system, a visual perception system, and a reinforcement learning system based on multimodal perception. The visual perception system acquires QR code target information and axis image information of the satellite parts; the force perception system acquires force and torque information at the end effector of the robotic arm; the acquired dual-view visual perception information is transmitted to the reinforcement learning system based on multimodal perception, where multiple decision networks are trained using a multimodal reinforcement learning algorithm to obtain a trained decision network. An admittance control algorithm is then used to output position and attitude adjustment strategies; the multi-degree-of-freedom spatial robotic arm system controls the robotic arm to complete the satellite assembly task. Using this invention can improve the efficiency of space robot satellite assembly.

This disclosure provides a fault diagnosis and self-healing control method for a pump cluster in a thermal power plant, relating to the field of intelligent automatic control technology for thermal power plants. The method includes: acquiring full-band acoustic signals from the pumps using an array of microphones; performing hierarchical decomposition, adaptive filtering, target acoustic band separation, feature extraction and dimensionality reduction, and principal component dimensionality reduction to obtain preprocessed target feature data; fusing the target feature data with pump operating parameters to reconstruct the state space of the target network and optimizing the reward function; outputting the probability distribution of fault types of the pump cluster based on the state space through a decision network in the target network; evaluating the output of the decision network through an evaluation network in the target network; and updating the decision network and evaluation network in conjunction with the reward function; and realizing fault diagnosis and self-healing control of the pump cluster based on the updated target network. This disclosure achieves automatic fault diagnosis and corresponding control in thermal power plants, ensuring the safe and efficient operation of thermal power plants.

This invention discloses a method and system for detecting embedded stones in potatoes using multimodal sensing and intelligent decision-making, specifically relating to the field of non-destructive testing and sorting of agricultural products. The invention involves triggering two sensors to acquire X-ray penetration images and ultrasonic echo signals when potatoes enter the detection area in a single column. The raw data is then preprocessed to generate standardized feature maps. Next, the preprocessed X-ray images and ultrasonic feature maps are spatiotemporally registered and input into a trained multi-channel deep learning fusion decision network. This network extracts deep features from both modalities in parallel, performs adaptive weighted fusion at the feature layer, outputs the classification probability of whether each potato contains embedded stones, and performs pixel-level localization of the stone locations. Finally, the intelligent decision-making network's judgment result and localization information are sent to the sorting execution mechanism in real time, removing potatoes containing embedded stones from the production line.

In order to solve the resource problem in the heterogeneous cloud computing environment, the application provides a batch processing task adaptive scheduling method based on pulse reinforcement learning. The technical path covers: multi-dimensional feature decoupling extraction is carried out on the input batch processing task, and clustering analysis is carried out; task classification is realized based on task characteristic attributes, and sorting is carried out according to priority; based on task analysis modeling, a pulse reinforcement learning resource scheduling model is established, and a double sparse attention mechanism is introduced to realize global state updating; the task scheduling environment of pulse reinforcement learning is constructed; the decision network and evaluation network of the pulse reinforcement learning model are constructed, and finally, in the simulation simulation scene, the trained model is used to realize the adaptive scheduling of batch processing tasks. The application fully considers the characteristic attributes of different tasks, overcomes the performance bottleneck of traditional scheduling algorithms in complex heterogeneous environment through accurate supply and demand matching strategy, and reduces the inference energy consumption during model training.

The application discloses a ship abnormal behavior identification method and system based on dynamic and static fusion and deep reinforcement learning. In the method, static electronic chart and ship AIS dynamic data are acquired; static environment element data is generated based on the chart, and AIS data is cleaned and verified to build dynamic environment elements; after fusion, spatial features are extracted by using CNN, and time sequence features are extracted by using LSTM; the above features are fused through a gate attention mechanism to obtain a joint state representation; and finally, a behavior category is output through a decision network based on deep reinforcement learning. The application effectively fuses dynamic and static environment information, and improves the accuracy and generalization ability of ship abnormal behavior identification in complex sea areas.

This invention belongs to the field of communication and network control technology. To address the problems of poor adaptability in non-ideal observation environments and the inability of a single optimization objective to meet various differentiated service requirements, and to overcome scheduling failures caused by network jitter or node failures leading to data loss, this invention provides: a time-sensitive network traffic scheduling method based on causal data completion. This method collects real-time traffic data from the current time-sensitive network (TSN) and constructs an irregular observation matrix; it uses a state reconstruction module based on neural Granger causality to complete the missing data in the observation matrix; it extracts robust spatiotemporal features with noise resistance from the completed observation matrix using a variational graph attention network; and it inputs these robust spatiotemporal features into a reinforcement learning decision network based on hierarchical optimization. Under the hard real-time constraint of priority critical time-triggered TT flow, it optimizes the best-effort BE flow transmission efficiency, ultimately generating a gated control list for execution. This invention is primarily applied in design and manufacturing applications.

The application discloses a load-driven unmanned aerial vehicle computing task regulation method and system, and the method comprises the following steps: constructing an unmanned aerial vehicle group motion model according to the positions and flight speeds of the unmanned aerial vehicles, wherein the unmanned aerial vehicles are configured with agents and a plurality of computing power cores; obtaining state observation information of the unmanned aerial vehicles based on the adjacency relationship between the unmanned aerial vehicles in the unmanned aerial vehicle group motion model; the state observation information comprises total energy consumption of the unmanned aerial vehicles, and the total energy consumption of the unmanned aerial vehicles at least comprises task transmission energy consumption between adjacent two unmanned aerial vehicles and computing power energy consumption of tasks executed by the unmanned aerial vehicles; inputting the state observation information into a target decision network in the agent to obtain unmanned aerial vehicle decision actions, wherein the unmanned aerial vehicle decision actions comprise task migration decisions and control decisions of the computing power cores, the energy consumption of the unmanned aerial vehicle cluster is minimized, the load balancing performance of the system is ensured, and the stability of the multi-unmanned aerial vehicle edge computing system is improved.

This invention discloses a method for determining obstacle avoidance strategies for warehouse robots, relating to the field of artificial intelligence technology. The system, during operation, includes: fusing data from LiDAR, inertial measurement units, and visual sensors to construct a dynamic environment model with semantic labels; generating behavioral intent vectors based on task type, urgency, and historical interactions, and forming a local collaborative intent graph through distributed communication; inputting the above information into a lightweight decision network to output obstacle avoidance strategies such as deceleration, lateral movement, detour, or slight waiting; and using a time-elastic band algorithm to plan a smooth trajectory that satisfies dynamic constraints, monitoring deviations during execution, and replanning locally when necessary. This application significantly improves obstacle avoidance efficiency, trajectory smoothness, and system robustness through context awareness, intent collaboration, and adaptive safety mechanisms, supporting the efficient and stable operation of large-scale robot swarms in high-density warehouse environments.

This invention discloses an intelligent decision-making method, terminal equipment, and storage medium for power system unit scheduling. Based on historical power system operating data, it extracts typical features using dimensionality reduction methods and constructs a feature index set by configuring feature weights using an objective weighting method. A Gaussian mixture clustering model is used for multi-scenario partitioning as a front-end optimization measure for deep reinforcement learning methods, mitigating the suboptimal decision-making problem that may be caused by differences in data distribution across multiple scenarios under source-load uncertainty. The unit scheduling problem is modeled as a sequential decision Markov process, constructing a multi-scenario unit scheduling model based on deep reinforcement learning, overcoming the limitations of the original single-scenario model. Through a dynamic step-size update mechanism and parallel computing, the parameter update efficiency during the offline training phase of the decision network is improved.

In various examples, systems and methods are disclosed relating to decider networks for reactive decision-making, including for control of robotic systems. The decider networks can allow robotic systems to operate more collaboratively, such as by allowing the robotic systems to more frequently process and react to dynamic states of the environment and objects in the environment, such as to change decisions and / or paths of decision execution responsive to dynamic changes in logical states. The decider network can include a plurality of nodes having functions to process the logical states in sequence to determine actions for the robotic systems to perform.

The application provides a black box confrontation evaluation method based on strategy driving and frequency-space residual remodeling, belongs to the technical field of confrontation attack, selects neural networks with multiple different network architectures to construct a heterogeneous agent model matrix, obtains a source detection tensor and a calibrated true value and extracts a benchmark response gradient; the current evolution state tensor, the benchmark response gradient, the frequency domain amplitude spectrum feature and the iteration progress scalar are spliced to form a multi-dimensional joint state vector; a frequency domain attenuation barrier and a space domain remodeling tensor are generated through a strategy decision network, the frequency domain filtering denoising and the space domain nonlinear residual remodeling are sequentially performed on the benchmark response gradient, and the evolution state tensor is updated in the residual fusion remodeling direction. After the multi-round iteration and the composite feedback signal optimization strategy network parameter, the tensor with the optimal comprehensive threat effectiveness is selected as the confrontation evaluation carrier output. The application can effectively strip high-frequency overfitting noise, solve the cross-model response offset problem, and improve the cross-model migration and evaluation stability of the black box confrontation evaluation carrier.

This invention discloses a kill net generation method and system based on offline reinforcement learning, relating to the fields of simulation and reinforcement learning. To address the problems of slow kill net generation speed, poor adaptability, reliance on manual intervention, and lack of end-to-end coordination in existing technologies, this invention performs scene modeling based on the tasks, resources, and dynamic factors involved in the simulation scenario, including state space, action space, reward function, and state transition rules. Based on the scene modeling, reinforcement learning interactive simulation is performed to obtain offline data containing simulation trajectories. The offline data is divided into multi-task segments to obtain a multi-task offline dataset, and a meta-reinforcement learning training is performed on the generative trajectory decision network. The trained generative trajectory decision network is then used to generate the target kill net. This invention can efficiently generate highly adaptable and automated kill nets, quickly respond to changing battlefield environments, reduce manual intervention, and improve generation efficiency.

Aspects of the subject disclosure may include, for example, a technique for processing a decision network that includes obtaining an index encoding a mapping from potential values of an input parameter to decision parameters of the network's predicates, wherein the mapping associates potential values of the input parameter with decision parameters affected by those potential values; evaluating decision parameters affected by specified values of the input parameter, including identifying each decision parameter to which the index maps at least one specified values of the input parameter, and setting the values of those decision parameters in accordance with the input parameter's specified values; and analyzing the decision network, including evaluating the predicates of one or more of the decision nodes based on the values of the predicates' decision parameters, and determining, based on the values of the evaluated predicates and a topology of the decision network, that a particular terminal node encodes the network's output. Other embodiments are disclosed.

The application discloses a rose planting medicine scheme decision method based on multi-modal feature fusion. First, multi-modal data of a rose planting area is collected, and the obtained multi-modal data is input into a feature fusion module for multi-modal feature fusion. A double-branch decision network is used for disease and pest type identification and medicine type and dosage determination, medicine proportioning rules are introduced through a medicine liquid mixing control module to correct the medicine type and dosage. Finally, through a user interaction optimization mechanism, closed-loop control is achieved, and the medicine scheme decision is optimized. The application realizes dynamic closed-loop decision by combining user feedback to adapt to the individual needs of different growers and solve the medicine application problems caused by data isolation and static decision in traditional rose planting. The application deeply couples artificial intelligence technology and agronomic knowledge to promote the transformation of traditional agriculture to intelligence and automation.

The application discloses a brain-computer interface signal processing method and system based on time sequence alignment and feature decoupling. In view of the problems of time asynchronization of electroencephalogram and near-infrared signal and feature entanglement caused by neurovascular coupling in the existing hybrid brain-computer interface, the application firstly extracts multi-scale features from the electroencephalogram signal and extracts multi-delay candidate feature sequences from the near-infrared signal; secondly, uses the electroencephalogram features as a query to guide a time delay attention mechanism to adaptively align the hemodynamic response features; then, projects the aligned features into shared and private subspaces through a multiple-constrained neural feature subspace decoupling module to separate the cross-modal neural intention and private physiological noise; finally, outputs a classification result through adaptive gating and multi-head decision network fusion. The application effectively overcomes the individual differences of neurovascular delay, strips the modality-specific noise, and improves the decoding accuracy and robustness.

The application discloses a kind of intelligent decision-making methods under the cooperation of spacecraft attitude orbit, by establishing spacecraft attitude coupling decision model, reasonably design reward mechanism, according to the relative position of target and itself, relative velocity, relative attitude, relative angular velocity, online real-time data collection and train the decision network weight of spacecraft, network output velocity increment and control torque, drive spacecraft orbit and attitude movement. After many iterations, the decision network weight converges to optimal value, output optimal decision strategy, so that spacecraft better completes orbit approaching task.

The application discloses a kind of stone surface image defect intelligent detection and real-time grading method, by the RGB image of the stone surface to be detected, thermal radiation image and depth image are synchronously collected, three modal images are respectively input corresponding feature extraction network and extract multi-scale hierarchical features, with cross-modal gate fusion module Channel inter-attention weight and spatial attention weight of each modal feature map are calculated respectively for each feature level and dynamically weighted fusion, generate unified cross-modal defect representation, then through grading decision network based on four semantic attributes mapping to continuous quality score space, configurable grading threshold output discrete quality level.The application utilizes the complementary characteristics of multi-modal information, solves the problem that single visible light image is difficult to accurately distinguish natural texture from real defect under complex texture background, while completely decouples defect objective attribute description and grading subjective standard application, significantly reduces deployment and maintenance cost.

This invention proposes a special equipment inspection system and method based on a multimodal large model, comprising: collecting and preprocessing multimodal data of special equipment; constructing a spatiotemporal fusion attention network for feature extraction to obtain fused feature representations; using a pre-trained multimodal large model for inference analysis, and distinguishing between normal and abnormal states through comparative learning; constructing a dynamic Bayesian decision network by combining historical data and an expert knowledge base to generate fault warnings and maintenance suggestions; optimizing inspection strategies based on equipment importance and warning levels; displaying inspection results through augmented reality and marking abnormal areas with digital twin technology to provide maintenance guidance. This invention can improve fault prediction accuracy, reduce false alarms and missed detections, optimize inspection paths, significantly reduce maintenance costs, extend equipment lifespan, and improve production safety.

This invention discloses an adaptive driving method for metal surface defect detection based on reinforcement learning, belonging to the field of metal surface defect detection technology. This method constructs a reinforcement learning state space for metal surface defect detection scenarios, extracting multi-dimensional state feature information from the input image in real time; it constructs an action space based on a visual detection model, including backbone and neck network parameter configurations; it designs a multi-objective reward function that integrates detection accuracy, inference efficiency, and small defect detection performance; it employs a two-stage training method, training the decision network through a proximal policy optimization algorithm; and finally, it dynamically selects the optimal model configuration based on real-time features to execute the defect detection task. This invention enables dynamic adaptive adjustment of detection model parameters, solving the problem that fixed models cannot adapt to multiple scenarios, balancing detection accuracy, inference efficiency, and deployment cost, improving the model's scenario adaptability, ensuring training stability and detection smoothness, and possessing feasibility for industrial application.

This invention discloses an autonomous flight control method for unmanned aerial vehicles (UAVs) based on multi-sensor fusion and AI decision-making, relating to the field of UAV control technology. The method includes: acquiring multimodal physical detection data of the UAV in its flight environment to generate a three-dimensional spatial airflow distribution matrix; constructing a multi-dimensional state space set; outputting a reference trajectory coordinate set and a high-frequency rotor compensation bias for the reference trajectory coordinate set through the dual-path action space of the strategy decision network; acquiring high-frequency vibration spectrum data of the UAV body; determining action triggering conditions based on the high-frequency vibration spectrum data; and using the reference trajectory coordinate set and the high-frequency rotor compensation bias to perform physical attitude correction on the UAV's underlying flight controller based on the triggering conditions, thereby controlling the UAV to perform obstacle avoidance flight. This invention improves the safety and stability of autonomous flight of UAVs in complex dynamic environments.

This application discloses an adaptive obstacle detection method and apparatus for adverse weather conditions, relating to the field of autonomous driving technology. The method acquires multi-source sensor data from an onboard vehicle, combines it with pre-calibrated sensor parameters to generate spatiotemporally aligned multi-source sensor data, extracts features to obtain feature maps for each modality, and projects all feature maps onto a bird's-eye view BEV space of the same resolution, using the LiDAR coordinate system as a reference, outputting a multi-modal BEV feature set. The feature set is concatenated along channels to form global state features, which are input into a pre-trained dual-branch adaptive decision network to obtain the output decision result, thereby generating the final image BEV features. Combining the multi-modal feature confidence weight matrix, the final image BEV features and the multi-modal BEV feature set are weighted to obtain globally fused BEV features, which are input into a 3D obstacle detection head for decoding and output detection results. This application can improve the robustness of multi-sensor fusion perception and obstacle detection accuracy under adverse weather conditions.

This application provides a data processing method for a large language model, a training method for a decision network, an apparatus, a device, a storage medium, and a program product. The method includes: constructing initial context data based on the input information to be responded to by the large language model; performing multiple iterative processing, each iteration including: encoding state features into the context data to be processed to obtain state features; performing feature mapping on the state features to obtain evaluation values ​​of multiple types of candidate actions in the action space, and determining the target action from the multiple types of candidate actions based on the evaluation values; stopping the iterative processing when the target action completes the generation of response data, and extracting the response data generated by the input information from the context data to be processed. This application enables adaptive selection of the target action through iterative evaluation of the current state, improving the flexibility of data processing and the accuracy of response.

This invention discloses a joint optimization method for edge computing-based vehicular network (V2N) resource management based on the DDPG algorithm. The method involves: establishing a network architecture integrating edge services and federated learning in the V2N, initializing network parameters; training a model using a dataset and calculating optimal model parameters; modeling the joint optimization problem as a Markov decision problem and training it using the DDPG algorithm, updating network parameters, recording the average reward, obtaining a decision network, and performing dynamic network offloading scheduling, resource allocation, and service model caching to achieve joint optimization of edge computing-based V2N resource management. This invention improves the real-time performance of V2N services based on edge computing and federated learning, exhibiting good convergence performance and joint optimization effects; it also enhances the security of privacy data on edge servers and the service quality for V2N users, and can be widely applied to practical mobile terminal applications such as path planning and navigation, and remote vehicle diagnostics.