37 results about "Swarm behavior" patented technology

The invention discloses a three-dimensional space unmanned aerial vehicle path planning method based on a swarm intelligence algorithm. The method comprises the following steps: S1, defining an initial boundary and sampling in the initial boundary to generate an initial population containing a plurality of candidate paths; s2, constructing a target function according to the optimization target; fitness values of the candidate paths are calculated based on the target function and the position function, and the candidate path with the high fitness value is selected as a global optimal solution; s3, the maximum number of iterations, the maximum number of iterations and the number of iterations of dynamic updating are set, and the specific number of iterations and the target probability are preset; introducing two dynamic parameters and designing a boundary adjustment coefficient, an adaptability factor and a dynamic probability which change along with the current iteration number; according to the method, autonomous navigation and path optimization of the unmanned aerial vehicle in a complex environment are realized by simulating the self-organization and distributed decision-making mechanism of group behaviors in nature, the path planning calculation speed can be effectively improved, the distance is reduced, and the adaptive capacity to environmental changes is enhanced.

The invention provides a sheep abnormal behavior real-time monitoring method and system based on the Internet of Things, and relates to the technical field of abnormal monitoring, and the method comprises the steps: obtaining multi-source data information of sheep, including a position coordinate sequence, motion sensor data, a gait rhythm sequence, a colony house environment parameter sequence and a group topological relation; the influence of environmental constraints on group movement is quantified by constructing a group behavior field intensity model; based on an individual physiological energy consumption backstepping mechanism, an energy metabolism imbalance index is identified by using a deep residual network; through Granger causal relationship and conditional independence analysis, behavior causal separation of true and false anomalies is realized; and performing cross-cycle abnormal evolution path prediction in combination with historical behavior data, and generating a graded early warning conclusion. According to the invention, the false anomaly and the real health anomaly caused by environmental factors can be effectively distinguished, and the monitoring accuracy and the early warning timeliness are remarkably improved.

The invention relates to the technical field of transformer optimization, and provides a transformer optimization design method and system based on a bionic swarm intelligence algorithm, and the method comprises the steps: determining an optimization target and a constraint condition of a transformer, the optimization target comprises the minimization of the total life cycle cost, and the constraint condition comprises the performance index limitation; based on the optimization target and the constraint condition, a parameterized transformer analysis model is constructed, and the parameterized transformer analysis model is used for calculating the total cost and performance indexes of the whole life cycle according to design variables; performing optimization solution on the parameterized transformer analysis model by applying a bionic swarm intelligence algorithm to search a global optimal design parameter combination on the premise of meeting the constraint conditions, the bionic swarm intelligence algorithm simulating biological swarm behaviors to perform global exploration and local development; and verifying the global optimal design parameter combination, and judging whether the global optimal design parameter combination meets all performance standards or not.

The invention discloses a method and a system for evaluating fertility of a tobacco field based on unmanned aerial vehicle remote sensing, and relates to the technical field of surveying and mapping service. Autonomous decision making is carried out at each node based on local information through a distributed game decision-making mechanism, the nodes do not follow a preset fixed path any more, but a flight decision is modeled as a non-cooperative game process, so that the fertility of the tobacco field is evaluated. The nodes are driven to preferentially fly to the grid area with the high information entropy value, when the multiple nodes fly to the same high-value area at the same time, the income reduction caused by mutual action is prejudged through game deduction, so that the nodes spontaneously and dispersedly negotiate and turn to other high-entropy areas which are not explored, and the dynamic path planning based on the real-time game has the advantages that the dynamic path planning efficiency is improved. According to the invention, the cluster behavior is converted from mechanical execution to intelligent planning, so that the non-repeated efficient scanning of the tobacco field range is realized under the condition of no central scheduling, and the problem of stiffness of a fixed path and the efficiency bottleneck of full-coverage acquisition are solved.

A method for controlling a driving function of a movable device, including a vehicle or a robot. The method includes: reading in parameters for controlling the driving function; using a map, wherein the map has at least a first region and a second region, wherein at least one value of a swarm behavior is entered in the second region; locating the device in the map; using the parameters to ascertain the driving function, if the movable device is in the first region of the map; using the at least one value of the swarm behavior to ascertain the driving function, if the movable device is in the second region of the map; controlling the device with the ascertained driving function. A method for creating a map for ascertaining a driving function of a movable device, a computing unit, a computer program, and a machine-readable storage medium, are also described.

The invention provides a task robot for a deep reinforcement learning system. The deep reinforcement learning system can utilize an asymmetric self-game algorithm to realize robust multi-robot clustering. The task robot comprises a reinforcement learning control module and an auxiliary training module. The control module can dynamically adjust behaviors of the robot to optimize decisions, and is characterized by comprising a target navigation model, a cluster behavior maintenance model and a collision avoidance model. The auxiliary training module enhances the environment perception capability, so that the robot can predict dynamic changes. The auxiliary training module comprises a local environment grid estimation model used for generating a small-scale map and a motion prediction model used for predicting tracks of a robot and an obstacle.

The invention provides an intelligent behavior identification and analysis method and system. The method comprises the following steps: segmenting preprocessed video stream data by using a semantic segmentation technology to obtain animal monomers, and respectively extracting spatial-temporal characteristics and overall dynamic characteristics of an animal group; inputting the spatio-temporal characteristics and the breeding environment semantic information into a monomer behavior semantic recognition model to obtain monomer behavior semantic characteristics, performing spatio-temporal correlation analysis on each monomer behavior semantic characteristic to calculate behavior interaction strength among different animal monomers, and constructing a group behavior correlation matrix according to each behavior interaction strength; and inputting the overall dynamic characteristics and the group behavior association matrix into a group behavior semantic recognition model to obtain a group behavior classification result, and generating prompt information. According to the method, key associated information such as group stress and ingestion competition can be effectively captured, and accurate identification and analysis of individual behaviors in a group behavior scene are realized.

The invention discloses a space-air-ground cooperative low-altitude security command and control method, system and device and a medium, and relates to the technical field of unmanned aerial vehicles, and the method comprises the steps: generating a global dynamic situation map according to multi-source detection data; performing cognitive analysis on the global dynamic situation map to obtain a system configuration, a key unit and a current confrontation stage of the unmanned aerial vehicle swarm; based on the system configuration and the key unit, predicting a subsequent confrontation stage of the unmanned aerial vehicle swarm after the current confrontation stage and a corresponding swarm behavior characteristic; according to the current confrontation stage, the subsequent confrontation stages and the group behavior characteristics, a multi-stage induction signal sequence is generated, and induction signals differentially configured for the subsequent confrontation stages are set to trigger the unmanned aerial vehicle swarm to generate a preset state response by using the group behavior characteristics of the subsequent confrontation stages, the preset state response is planned as a favorable condition for executing the next-stage induction signal. The method has the effect of improving the concealment of confrontation.

This application discloses a leader-based UAV swarm behavior control method, system, and device, relating to the field of UAV control technology. The method uses control force parameters and time-varying control parameters to control the behavior of a leader UAV, expanding the traditional fixed parameter model to a time-varying parameter model. By sending time-varying control parameters to control the behavior of follower UAVs, the behavior of the UAV swarm is controlled, enabling distributed control. This reduces communication resource usage and effectively enhances the scalability of the UAV swarm.

This invention discloses a method for creating fish habitats based on swarming effects, belonging to the fields of fish ecological engineering and water conservancy engineering. Existing technologies for creating fish habitats suffer from incomplete quantification of swarming behavior and a lack of quantitative correlation with engineering design parameters, leading to habitats that are difficult to match the needs of fish swarming. This invention quantifies spatial aggregation, movement synchronization, and turbulent adaptability, calculates a comprehensive swarming index and a group spatial demand coefficient, establishes a direct conversion model between swarming behavior indicators and habitat design parameters, and determines flow field control methods and structural layout methods based on the comprehensive swarming index and the group spatial demand coefficient, thereby creating fish habitats. This invention can comprehensively characterize swarming behavior, scientifically guide engineering design, and improve habitat applicability and utilization.

This invention provides a behavior recognition method based on single-view UAV swarm trajectory analysis, comprising: acquiring a large amount of raw single-view UAV swarm trajectory data, processing and manually labeling it, then dividing it into training and testing sets, wherein the labeled tags include behavior category tags and attribute tags; designing a multi-task UAV swarm behavior recognition model based on dual-branch feature fusion for the task objective of single-view UAV swarm behavior recognition, and training and testing the UAV swarm behavior recognition model using the labeled dataset to obtain a trained UAV swarm behavior recognition model; and using the trained UAV swarm behavior recognition model to perform behavior recognition on the single-view UAV swarm trajectory data to be identified to obtain the recognition result. This behavior recognition method significantly improves the accuracy and interpretability of single-view UAV swarm behavior recognition and can simultaneously output fine-grained swarm state attributes.

The embodiment of the invention provides an animal social analysis method and device, electronic equipment and a medium, and belongs to the technical field of artificial intelligence. The method comprises the following steps: extracting a global video frame sequence from a real-time multi-view video of an animal group; performing real-time group behavior recognition, individual behavior recognition and animal posture recognition on the global video frame sequence, and performing social contact pointing analysis on the animal group according to group social contact behavior categories, single animal behavior categories and target animal posture data obtained through real-time recognition to obtain group social contact pointing data; and according to the group social behavior category, the single animal behavior category and the group social pointing data, social information integration is carried out to obtain target animal social data. According to the embodiment of the invention, the social directivity analysis is carried out according to the group social behavior category, the single animal behavior category and the target animal posture data, so that the social directivity of the animal group social behavior can be accurately judged in real time, and the efficiency and precision of animal social analysis are improved.

This invention discloses circular RNA circLOCMI02072 (1, 2） Its application as a behavior regulator in locusts falls under the field of agricultural biotechnology. This invention discovers circular RNA. circLOCMI02072 (1, 2） The expression of this circular RNA differs between gregarious and solitary locusts, and its expression level is negatively correlated with locust swarming behavior. Increasing the expression level of this circular RNA in locusts can significantly inhibit locust swarming behavior. This invention provides a novel, green, and pollution-free locust control technology that is highly efficient, specific, and environmentally friendly, and has important application value for locust control.

This invention provides an AI-based intelligent scheduling method for construction equipment, belonging to the field of construction scheduling technology. This AI-based intelligent scheduling method constructs a three-layer intelligent scheduling framework: macro, meso, and micro. The macro layer uses an improved time series prediction algorithm to deeply integrate the construction cycle and external events, achieving accurate and forward-looking resource planning. The meso layer employs a combined auction algorithm to quantify equipment synergy, optimize task allocation, and significantly improve the efficiency of multi-equipment joint operations. The micro layer utilizes a distributed negotiation mechanism to simulate swarm behavior, endowing the system with strong self-organization and dynamic adaptability. Supplemented by a resilient scheduling algorithm, it continuously monitors system health and automatically recovers. Through dynamic weighted multi-layer decision-making, it ensures the system maintains stable and efficient operation under various disturbances.

The invention discloses a bird migration process action classification method based on machine learning, and aims to solve the problem of action classification ambiguity caused by the fact that the same posture corresponds to various behaviors in monitoring. Constructing a group heterogeneous graph in combination with trajectory information, introducing migration stage priori, and learning group context features in a group graph Transform; and inputting the individual features, the group context features and migration stage priori into an action classification network to obtain the action probability distribution and prediction uncertainty of each bird, adjusting the priori weight by using the difference between the group behavior distribution and the migration stage expected behavior distribution and combining the prediction uncertainty, and performing joint correction on the action probability distribution to obtain the bird movement probability distribution. Group behavior distribution approaches stage prior, and the technical effects of relieving attitude ambiguity in a migration scene and improving the accuracy of bird migration process action classification are achieved.

The invention relates to a pedestrian trajectory prediction method combining a Kalman filter and an attention mechanism recurrent neural network. The method comprises the following steps: S1, multi-modal perception and dynamic interaction modeling; S2, time-space interaction driven trajectory prediction; S3, Kalman filtering-based trajectory optimization; the framework inherits the theoretical advantages of heterogeneous interaction modeling and time sequence consistency optimization, the adaptability of the model to group behaviors is enhanced while the noise interference of the sensor is reduced, high-precision and robust trajectory prediction is finally realized, and after multi-modal detection data is processed by the attention network, the multi-modal detection data is dynamically optimized through Kalman filtering, so that the robustness of the model is improved. And a reliable decision basis is provided for service robot navigation.

The application discloses a kind of based on genetic algorithm's robot colony behavior logic generation method and system, comprising: obtaining the condition information perceived by each robot in robot colony, constructs condition library;Obtain all actions executed by each robot facing multi-target task scene, construct action library;According to condition library and action library, construct behavior tree;By the matrix genetic algorithm of pre-construction, obtain multiple matrices generated by multiple behavior trees associated by robot colony conversion, after genetic operation to multiple matrices, by condition filtering mechanism, delete useless condition in condition library and useless condition action line in matrix, and when meeting evolution termination condition, output the highest fitness value of target behavior tree;According to target behavior tree, obtain the behavior logic of robot colony facing multi-target task scene.The application optimizes behavior tree that can be converted into matrix by matrix genetic algorithm, and automatically generates the behavior logic of robot colony facing multi-target task scene.

The invention discloses a drug design optimization and precision medical analysis method and system based on swarm intelligence. According to the method, behaviors of weak meat and strong food groups are simulated, candidate drug molecules or patient pathological models are regarded as agents, and core data of the agents are protected by hiding virtual models; risks such as toxicity and off-target effect are actively identified and avoided through the security defense model; the intelligent agent is guided to escape from the local optimal solution and the invalid research and development path through the escape model; and finally performing fusion and multiple verification on the elite agent through the survival model, and outputting high-quality and low-risk candidate drug molecules or personalized treatment schemes. According to the method, a safe and anti-interference mechanism is embedded in an optimization process, the efficiency and success rate of new drug research and development are remarkably improved, and a powerful analysis tool is provided for precision medical treatment.

The invention discloses an insect condition forecasting system and method based on a lightweight neural network and terminal cloud cooperation. The system comprises an edge sensing device and a cloud server. After the insect activity is detected, the edge sensing device is used for extracting behavior fingerprint characteristics of the detected insect according to the insect image sequence and sending the behavior fingerprint characteristics of the detected insect to the cloud server; the cloud server determines the behavior category of the detected insect according to the behavior fingerprint features and the standard behavior features; performing space-time correlation retrieval according to the behavior category of the detected insect to obtain a correlation behavior chain; and determining whether a group behavior occurs or not according to the associated behavior chain. The system provided by the invention is relatively good in real-time performance and relatively small in error.

This invention discloses a method and system for simulating and alleviating stress in pigs based on multi-dimensional environmental parameters. The method includes: constructing a digital twin environment of the pigsty, simulating and updating the effective ambient temperature, conductive ground temperature, and ammonia concentration in real time; constructing multiple pig agents and calculating core body temperature changes based on the physiological energy equation; using an improved Boids swarm algorithm to drive emergent group behavior of the pig agents, where the cohesion weight is dynamically adjusted according to environmental parameters: nonlinear enhancement at low temperatures to simulate swarming, decaying to a negative value at high temperatures to simulate dispersion, and applying negative feedback decay and superimposing random noise to simulate social disturbance when ammonia levels exceed the standard; updating environmental parameters in response to user environmental control operations, and repeating the above steps to form a closed loop until the stress is relieved. This invention solves the problem of existing simulation systems lacking closed-loop dynamic simulation and can be used for livestock teaching and research training.

The invention discloses a fish habitat building method based on a group swimming effect, and belongs to the field of fish ecological engineering and hydraulic engineering. In the prior art, the fish habitat building has the problems that the quantification of the fish habitat is not comprehensive, and the association with the quantification of engineering design parameters is lacked, so that the habitat is difficult to match the fish swarm swimming demand. According to the method, the space aggregation degree, the motion synchronism and the turbulence adaptability are quantified, the comprehensive cluster index and the group space demand coefficient are calculated, a direct conversion model of group travel as an index and habitat design parameters is established, and the flow field regulation and control mode and the structural layout mode are determined based on the comprehensive cluster index and the group space demand coefficient. Therefore, a fish habitat is built. According to the method, group travel behaviors can be comprehensively described, engineering design is scientifically guided, and the applicability and utilization rate of the habitat are improved.

Method (100) for controlling a driving function (5) of a movable device (1), in particular a vehicle or a robot, comprising the steps: - Reading (110) parameters (6) for controlling the driving function (5), - Using (120) a card (15) wherein the card (15) has at least a first area (16) and a second area (17) wherein at least one value of a swarm behavior (9) is entered in the second area (17), - Locating (130) the device on the map (15), - Using (140) the parameters (6) to determine the driving function (5) when the movable device (1) is in the first area (16) of the map (15), - Using (150) at least one value of the swarm behavior (9) to determine the driving function (5) when the movable device (1) is in the second area (17) of the map (15), - Controlling (160) the device with the determined driving function (5). Furthermore, the invention comprises a method for creating a map for determining a driving function of a movable device, a computing unit, a computer program and a machine-readable storage medium.

This invention relates to an adaptive aircraft swarm control system and method. Each aircraft in the swarm includes: an intelligent master control scheduling module, a tacit consensus module, a communication adaptive interaction module, a multi-source situational awareness module, and a multi-task coupled decision-making module. This invention employs a swarm control system mounted on each aircraft, enabling compatibility with both centralized and distributed collaborative models and achieving closed-loop collaboration of swarm tasks such as perception, decision-making, and communication. Through the offline construction and online updating of multi-source consensus information by the tacit consensus module, the consistency of swarm behavior and task collaboration are maintained even in weak communication environments such as localized, intermittent, and delayed communication. This invention effectively solves the challenges of collaborative decision-making, situational awareness sharing, and task execution in intelligent swarm systems under extreme communication interference conditions.

This invention discloses a dynamic task allocation method for UAV swarms based on coyote pack prey selection behavior: Step 1: Initialize UAV swarm air combat conditions; Step 2: Execute target selection tasks based on coyote pack behavior mechanisms; Step 3: Generate strike formations based on coyote hunting time window constraints; Step 4: UAV swarm executes strike / tracking tasks; Step 5: Update the air combat scenario map; Step 6: Reassign UAV swarm combat tasks. This invention addresses the problem of dynamic task allocation for tactical reconnaissance and strike integrated UAV swarms in air combat environments. Considering the dynamic real-time situation of the combat environment and the potential collaborative relationships of enemy swarms, it provides a dynamic task allocation method based on coyote prey selection behavior. This method prioritizes striking weaker targets, suppresses opportunities for enemy UAV situational shifts, reduces enemy swarm support and counter-encirclement, and effectively improves the combat effectiveness of UAV swarms.

This application discloses a path planning method, apparatus, device, and medium based on a swarm collaborative optimization algorithm, comprising: generating a population; determining environmental complexity based on obstacle density factor, straight path blocking factor, and obstacle distribution factor; determining the current theoretical path points based on environmental complexity; and determining the actual path points based on the current theoretical path points and the previous generation's optimal path points; in each iteration loop, performing a global search on each individual based on a first random number and swarm behavior parameters; performing local development on each individual based on a second random number, swarm behavior parameters, and the global search result; updating the individual's historical optimal solution and the current global optimal solution based on the local development results; updating the optimal path points based on the basic path points and the actual path points; and outputting the global optimal solution when the number of iterations is a preset number of rounds, thereby enhancing the global exploration and local development capabilities and improving adaptability and search efficiency in dynamic environments.

The invention relates to a group mixed type hunting control method based on a space-time alternate layered leader structure, and belongs to the technical field of robot groups. The task execution efficiency and robustness in a space-time dynamic environment are optimized in combination with bionic principles such as a space-time alternate layered leader structure, informed leader and a hybrid hunting control strategy of biological population behaviors. According to the method, space-time alternate layered leader structure characteristics existing in biological group behaviors are applied to a control method of a robot group, the cooperative behaviors of the robot group are optimized, and a bionic group hybrid hunting control method is provided, so that more robust, efficient and flexible cooperation of the robot group in the dynamic hunting process is realized.

To explanatorily present a network among individuals in a group.SOLUTION: A group action analysis device 100 comprises: a synchronous calculation part (synchronous calculation program 152) which estimates causality among individuals in each combination of a plurality of individuals from sensor data 161 acquired from the plurality of individuals, estimates, for each combination of the plurality of individuals, a distance between individuals and a direction of the other individual viewed from one individual from the sensor data 161, and also estimates accuracy of recognition between the individuals based upon the estimated distance between the individuals and the directions of the individuals; and a network display part (network display program 153) which displays a network among the individuals in group action based upon the causality among the individuals in each combination of the plurality of individuals and the accuracy of the recognition which are estimated by the synchronous calculation part.SELECTED DRAWING: Figure 1

This application discloses an autonomous anisotropic deformation robot module and a swarm robot system. The robot module includes a central base, an outer frame, multiple first drive components, and multiple second drive components. The outer frame includes multiple movable ends, with adjacent movable ends connected by elastic elements. Each movable end is equipped with a first magnetic element. Each first drive component and second drive component connects a movable end to the central base and is adapted to drive the corresponding movable end to move radially outward or inward along the central base. The first drive components and second drive components are alternately spaced along the circumference of the central base, and their driving directions are opposite. The swarm robot system includes multiple robot modules, and swarm behavior is achieved by adjusting the deformation phase and connection topology of the robot modules. This application is low-cost and simple to manufacture, reducing manufacturing costs and process difficulty, simplifying the system control strategy, and enabling diverse swarm behaviors under different parameter combinations.

This application discloses a method, system, equipment, and medium for low-altitude security command and control using a combined air-space-ground approach, relating to the technical field of unmanned aerial vehicles (UAVs). The method includes: generating a global dynamic situation map based on multi-source detection data; performing cognitive analysis on the global dynamic situation map to obtain the system configuration, key units, and current confrontation stage of the UAV swarm; predicting subsequent confrontation stages and corresponding group behavior characteristics of the UAV swarm after the current confrontation stage based on the system configuration and key units; and generating a multi-stage induction signal sequence based on the current confrontation stage, subsequent confrontation stages, and group behavior characteristics. The induction signals, configured differently for each subsequent confrontation stage, are set to trigger a preset state response of the UAV swarm using the group behavior characteristics of that subsequent confrontation stage. This preset state response is planned as a favorable condition for executing the next stage induction signal. This application has the effect of improving the concealment of confrontation.

The invention discloses a cognitive driving space behavior modeling method based on inverse reinforcement learning. The method comprises the following steps of space behavior data collection, initial agent setting, environment cognitive feature extraction, space behavior modeling, behavior mechanism analysis and data library building and visualization. According to the method, a space-behavior model capable of reflecting visual cognition, functional cognition and community cognition is formed by introducing a video track and space environment data and combining optimal path baseline setting and inverse reinforcement learning training; accurate prediction and mechanical explanation of crowd behaviors in a public space can be realized, and the method is suitable for application scenes such as space design optimization, group behavior simulation and smart city management.