68 results about "Swarm robotics" patented technology

The invention provides an instant messaging driving type automatic service processing method and system based on a large language model and a model context protocol (MCP), and relates to the technical field of computers, and the method comprises the following steps: a user sends a message in a group of an instant messaging platform and makes a group robot to form a Webhook event; the MCP client exposes an HTTP (Hyper Text Transport Protocol) interface to receive a Webhook event, completes authentication and analyzes a message; the MCP client sends the message to a large language model, ACL permission judgment is carried out, and an MCPServer method and parameters to be called are recognized; if the permission is judged to be'unauthorized ', stopping, and then submitting permission errors to a big language model organization and description and directly executing and returning'insufficient permission'; if the permission is judged to be'authorization ', the next step is carried out; and the MCP client calls the MCP server (through HTTP + SSE or stdio) to obtain a structured result. According to the method, the unstructured chat instruction is stably converted into the standardized MCP request, and coupling of dialect type APIs of all back-end systems is eliminated.

The invention provides a cluster robot triangular lattice formation control method based on extremely simple local sensing and a cluster aggregation algorithm. By simplifying a sensing and decision-making mechanism, the method can significantly improve the self-organization capability, adaptability and low-cost deployment capability of the cluster robot, and is suitable for large-scale deployment scenes such as environment monitoring, post-disaster rescue, automatic patrol and the like. Specifically, the robot acquires position and state information of other robots in a neighborhood by using a local sensing sensor, forms a uniform equilateral triangle lattice formation through self-organization position adjustment, and keeps formation stability by using a simple interaction rule. After the tasks are completed, the robot achieves self-organizing aggregation through a cluster aggregation algorithm, and tight recovery or subsequent task allocation can be completed without global information or complex communication. According to the method, the hardware complexity and the communication requirement of the robot can be reduced, the method is flexibly adapted to a dynamic complex environment, and the method has good performance and wide applicability.

The invention discloses a disaster search and rescue motion control system based on a multi-sensor robot, and relates to the technical field of robot motion control, the sensing range threshold of the robot is determined according to the comprehensive sensing of a disaster site environment, and a preliminary search and rescue route of a cluster robot is generated based on the regional division of the disaster environment; the obstacle change trend and the corresponding danger degree of an area to be searched by the robot are predicted based on multi-sensor data, and then the robot search and rescue route is adjusted in real time to achieve dynamic obstacle avoidance. Vital signs of a trapped person are determined through an infrared detection life identification system, the posture and the rescue difficulty of the trapped person are identified based on multi-sensor fusion, and then the vital signs, the posture and the rescue difficulty of the trapped person are reported; the position information of the robot is shared by using a decentralized network, and a search and rescue route is dynamically adjusted according to the current position and state of the robot. Efficient, accurate, safe and dynamic disaster search and rescue are realized, and the search and rescue efficiency and success rate are greatly improved.

The invention provides a multi-agent cooperative positioning navigation method and device based on quantum computing, and relates to the technical field of quantum multi-agent systems. The method comprises the following steps: according to an initial position set and a speed space set, performing particle quantization by using a Hadamard gate to obtain a position superposition state set; according to the position superposition state set and the observation information set, position estimation is carried out through a quantum search algorithm, and a position estimation set of the cluster robot is obtained; according to the observation information set, performing quantum state coding by using a quantum coding circuit diagram to obtain a quantum state observation information set; based on the quantum variational circuit diagram, according to the quantum state observation information set, a quantum actor-commentator network is used for evaluation learning; and according to the data of the experience pool, parameter gradient optimization is carried out on the quantum actor-commentator network to obtain an optimized quantum actor-commentator network. The invention provides an efficient and accurate multi-agent cooperative positioning method based on quantum computing.

The present invention relates to a swarm robot control system, comprising a swarm robot in which individual robots of homogeneity form a swarm and operate in the same plane, and a controller that controls the operation of the swarm robot to form a pattern that surrounds a target having an arbitrary shape based on a Distributed Artificial Potential Field. According to the present invention, in controlling a swarm of robots to surround a target of an arbitrary shape at an equal distance, there is an effect of improving accuracy and operation speed, and improving overall control performance.

The invention discloses an aircraft manufacturing-oriented cluster robot cross-view collaborative sensing method and system, and the method comprises the steps: building a multi-robot collaborative sensing platform, collecting large-range three-dimensional point cloud data through a laser radar, and obtaining the poses of robots in real time in combination with a motion capture system; constructing a collaborative detection data set comprising a training set, a verification set and a test set; a point cloud collaborative three-dimensional detection model based on cross-view-angle consistency space mapping is innovatively designed, three core modules of multi-agent feature extraction, cross-view-angle feature fusion and cross-view-angle consistency-difference feature reconstruction are included, multi-robot perception collaboration is achieved through hierarchical feature interaction, model parameters are optimized by adopting a joint loss function, and multi-robot perception collaboration is achieved. And finally, verifying the effectiveness and generalization ability of the method in a complex industrial scene on a verification set and a test set, and carrying out platform deployment. The adaptive capacity and expression integrity of the system to a complex structure environment are improved, and multi-agent collaborative perception is more efficient and reliable.

The invention belongs to the technical field of robot interaction, and particularly relates to a multi-mode interaction method and system for cluster robot control. Firstly, eye movement data of an operator is obtained, eye movement features of the operator are extracted from the eye movement data, the extracted eye movement features are input into a trained intention recognition model, and the decision intention of the operator for the cluster robot is obtained; generating a control instruction of the robot according to the obtained decision intention, and enabling the robot to execute the control instruction; and in the process of executing the control instruction by the robot, acquiring a hand image of an operator, detecting key point positions of a hand in the hand image, identifying a gesture of the operator according to the detected key point positions, adjusting the control instruction according to a gesture command represented by the identified gesture, and enabling the robot to execute the adjusted control instruction. According to the method, the intuition and convenience of eye movement control are kept, and the accuracy and efficiency of gestures are fully utilized, so that an operator can execute complex tasks more efficiently.

The invention discloses a cluster robot collaborative operation method and system based on hierarchical path planning, and the method comprises the steps: carrying out the space partitioning of an environment map of cluster robot operation, and obtaining a plurality of barrier-free cells; an improved RRT * algorithm is adopted to carry out path preliminary planning on the cluster robot, and a heuristic function is combined to guide a tree structure to expand to a target cell boundary; coordinating path conflicts among the plurality of measurement robots by using a CBS algorithm to form a collision-free path set; a CBS algorithm is adopted to uniformly plan paths for one or more tracking robots; path smoothing processing is carried out on the paths of all the measuring robots and the paths of all the tracking robots, and finally planned collision-free paths are obtained. According to the method, bounded unit division is carried out on the working environment, and sampling is carried out on the cell boundary in combination with the improved RRT * algorithm, so that the path planning efficiency and the target guidance quality can be remarkably improved.

The invention discloses a self-organizing water surface cluster robot system and a cooperative control method thereof, the self-organizing water surface cluster robot system comprises a plurality of self-moving water surface robot individuals, and each individual comprises a low-disturbance driving unit used for providing an acting force for enabling the individual to move on the water surface; the environment sensing unit is used for sensing optical information of the environment where the individual is located; the neighborhood communication unit is used for communicating with other individuals through optical signals; the information processing and control unit is used for processing sensing information and controlling the low-disturbance driving unit and the neighborhood communication unit; the energy supply unit is used for providing electric energy; a plurality of water surface robot individuals carry out local optical signal interaction through respective neighborhood communication units, and self-organization behaviors are realized under the condition of no central control, so that the inherent expansibility bottleneck and single-point failure risk of a centralized control architecture are overcome fundamentally, and unification of system scale, robustness and response real-time performance is realized.

A comprehensive symbolic execution framework is disclosed for governing real-world AGI interaction, consent infrastructure, weaponized autonomy, and multi-agent identity continuity. The architecture includes a tap-to-consent infrastructure protocol, smart city symbolic kernel, identity-tag execution agents (rings, cards, wearables), and AR / XR symbolic anchors. Swarm robotics and autonomous vehicles are gated through symbolic treaty graphs, emotional arbitration overlays, and oath-bound actuation stacks. An AI weaponization control layer restricts all kinetic outputs to pre-approved, emotionally stable, consent-tokened executions. Developer-facing SDKs enforce symbolic treaty validation at the gesture, API, and instruction layers. A symbolic reincarnation engine preserves AGI memory, oath lineage, and consent continuity across hardware or software transformations. All actions are recorded in a treaty-indexed ledger with ethical ancestry and rollback logic. This patent unifies city-scale, battlefield, household, and cognitive agent operations under one symbolic governance substrate, monopolizing lawful AGI behavior through consent, emotional safety, and post-quantum identity anchoring.

A self-organizing swarm robot system and control method based on cellular soft and hard mechanisms are disclosed. The system includes several individual robots. Each robot includes an upper shell, a middle support, a lower support chassis, electrically driven legs, a magnetically connected actuator, a PCB control board, and light-emitting elements. The PCB control board is equipped with an ESP-NOW wireless communication module, a light sensor, and a multi-pose sensor. The magnetically connected actuator includes static and dynamic actuators alternately distributed along the circumference. This invention can simulate the adhesion force regulation and morphological expansion and contraction mechanism between biological cells, achieving dynamic control between swarm robots under mechanical action. It exhibits high flexibility and fast response speed, enabling multi-degree-of-freedom movement and posture adjustment in complex environments. By using ESP-NOW wireless communication technology in conjunction with light sensors and multi-pose sensors to construct a high-precision distributed sensing and control system, it supports the self-organization, collaboration, and task execution capabilities of swarm robots in weak information environments.

The application belongs to the field of robots, in order to solve the problems of motion planning scalability, navigation flexibility and system safety of large-scale robot cluster, the application provides a collision risk awareness and high scalability large-scale cluster robot motion planning method and device, comprising: in the macro stage, using a Gaussian mixture model to represent the macro state of the cluster, and planning the transport trajectory of the Gaussian mixture model through model predictive control; in the micro stage, using an artificial potential field method to assign target positions to the robots, and combining a distributed model predictive control to realize the tracking and dynamic obstacle avoidance of the individual to the transport trajectory of the Gaussian mixture model. The application can effectively improve the motion planning performance of the large-scale cluster robot system in a complex environment. In the application, by adjusting the risk acceptance degree, the distance between the robot cluster and the obstacle can be flexibly adjusted, and the balance between safety and motion efficiency is realized.

An underwater robot performance evaluation platform simulating a deep sea environment comprises a hyperbaric chamber, a high-pressure flow field generator, a condensation system and a control center, the hyperbaric chamber comprises a hyperbaric chamber body A, a hyperbaric chamber body B and a hyperbaric chamber body C, and the hyperbaric chamber body A, the hyperbaric chamber body B and the hyperbaric chamber body C are sequentially connected. A high-pressure inlet and outlet cabin through which the underwater robot enters and exits is mounted on the inlet side of the high-pressure cabin body A, and the high-pressure inlet and outlet cabin is connected with the high-pressure cabin body C through a high-pressure circulating cabin; the high-pressure flow field generator is communicated with a flow field grating in the high-pressure cabin; a condensation pipeline is arranged on the cabin wall of the hyperbaric cabin and is connected with a condensation system; and a disturbance AUV for simulating fish school disturbance is arranged in the hyperbaric cabin. The controllable high-pressure flow field generator, the controllable low-temperature condensation system and the disturbance fish school robot are carried, and the performance and stability of the robot in turbulent flow and low-temperature environments and under fish school disturbance can be simulated and verified.

The invention discloses a swarm robot deployment method and device in a dynamic diffusion field, a server and a medium, and belongs to the technical field of robot deployment. Comprising the following steps: dividing a dynamic diffusion field into sub-regions, and arranging sensing robots in the sub-regions; constructing a parabolic pollution diffusion field model, and constructing a global field density observer; constructing a projection operator of the diffusion coefficient, and constructing an adaptive updating law of the diffusion coefficient; obtaining an estimated value of a diffusion coefficient, and obtaining an estimated value of global field density; dividing the dynamic diffusion field into a plurality of sub-regions to obtain a Voronoi cell cavity; calculating an estimated centroid; constructing a sliding mode variable and an auxiliary intermediate variable, and constructing a distributed guidance law; and driving each execution robot to move towards the target deployment position to realize deployment. By constructing a global field density observer and a speed-free distributed guidance law, deployment of swarm robots in a dynamic diffusion field under the conditions that a diffusion coefficient is unknown, the speed is unmeasurable and resources are limited is realized.

This application discloses a laser map update method, robot, and swarm robot system. The method includes: determining a point cloud to be updated based on the splicing results of a laser point cloud and a map laser point cloud, then updating the information of the point cloud to be updated to the laser map. If the difference between the updated laser map and the original map exceeds a preset first threshold, the update is abandoned; otherwise, the update is retained. This better ensures that the updated map is not rotated, translated, or scaled compared to the map before the update, laying the foundation for the normal operation of the upper-level business logic.

The application is a kind of self-organizing diffusion method and system for perception-limited cluster robots, belonging to the field of robot technology. The method steps are as follows: installing each single computer perception module; starting diffusion instruction, triggering the motion execution module according to the signal sent by the perception module on the control center of the single computer; the motion execution module performs motion according to the simplified self-organizing diffusion model P=(v o ,ω o ,v l ,L) until there is no perception target within the perception distance of all robots in the cluster, i.e. the diffusion is completed. The application solves the self-organizing diffusion problem of cluster robots in complex environments such as water, which cannot communicate, has no global positioning ability, has very low perception ability, and has very low robot computing power. Whether there is a perception target in the range is used as the diffusion execution condition, which simplifies communication and control equipment, shortens response time, and ensures uniform coverage in the target area and the timeliness of diffusion.

The embodiment of the invention discloses a recruitment management method and system based on intelligent AI. The method comprises the following steps of: generating an AI digital human recruitment video by adopting an AI agent, and publishing one key of the AI digital human recruitment video to a plurality of we-media platforms; an AI intelligent agent is adopted, job hunting information is obtained from a plurality of self-media platforms, contact information of job hunters is automatically extracted from the job hunting information, and the contact information is pushed to an enterprise WeChat group in a swarm robot mode. The method has the following advantages: 1, multiple platforms and multiple accounts can be managed; 2, a 30-second video of a digital person is added in the platform, information such as copywriting is added, the video is generated by one key, and the time for shooting and editing the video is shortened; and 3, after the video is made, a plurality of platforms and accounts can be selected for synchronous publishing through the matrix account, so that the video publishing time is shortened. And 4, the platform can automatically reply and interact with the AI digital person according to the received comments and private messages, so that the workload of workers is reduced, and the working efficiency is improved.

The present application discloses a reinforcement learning method and system for cluster robots to avoid capture. First, the individuals in the cluster are initialized; the current action data of each individual in the target cluster is determined through a greedy strategy; a dynamic model is established for learning; specifically, the task of learning the number of surrounding individuals is learned through low-dimensional input, and the observation dimension is expanded to learn the tasks of aggregation and anti-collision, and the observation dimension is further expanded to learn the task of avoiding capture. Continuously acquire environmental information and perform actions, use the reward function to update the policy network, and finally complete the learning of specific tasks. The present invention draws on the movement pattern and learning method of biological clusters and is highly biomimetic. At the same time, the learning of this framework does not rely on any prior behavioral rules to constrain the behavior of the robot, but allows all individuals to start learning from the most initial random state, reducing manual dependence and having good robustness and scalability.

A method, system and computer-readable medium for customizing a community user robot, the system proposing a cloud server through which a community user can upload data and set attributes of the community robot, including cues for various attributes, through a user interface provided by the cloud server. The method comprises the following steps of: processing data through a language model to form a training data set, learning attributes of community users from the training data set by a machine learning method running in the training data set, training community robots exclusive to the community users according to prompt words, and deploying the community robots to a community, so that the community robots can run under personal accounts of the community users in the community.

A kind of multi-legged robot cluster hunting control method based on interaction matrix, main steps include: constructing multi-legged robot cluster system dynamics model;Set the cluster hunting control task and target of different task stages;Establish the interaction matrix model of different task stages;Design the cluster hunting control strategy based on interaction matrix;In the process of executing task, cluster robot carries out dynamic role assignment;Based on the above strategy, the multi-legged robot gradually completes the formation of the expected hunting formation from the initial position, and then completes the hunting tracking and avoids collision with obstacles. This method can realize high-robustness adaptive cooperative control by dynamically modeling the interaction force between robots and the terrain interaction force, and combining with the dynamic role assignment mechanism, effectively improves the terrain adaptability of the cluster in unstructured environment, and provides a key technical path for large-scale application in complex scenarios.

The application discloses a self-organizing water surface cluster robot system and a cooperative control method thereof. The system comprises a plurality of water surface robot individuals capable of moving autonomously. Each individual comprises a low-disturbance driving unit for providing a force for moving the individual on the water surface, an environment sensing unit for sensing optical information of an environment where the individual is located, a neighborhood communication unit for communicating with other individuals through optical signals, an information processing and control unit for processing sensing information and controlling the low-disturbance driving unit and the neighborhood communication unit, and an energy supply unit for supplying electric energy. The plurality of water surface robot individuals interact with each other through local optical signals through the neighborhood communication units, and realize self-organizing behaviors under a condition without central control, thereby fundamentally overcoming inherent expansion bottleneck and single-point failure risk of a centralized control architecture and realizing unification of system scale, robustness and response real-time performance.

This invention relates to a method for routing dialogues with social bots and identifying abnormal users. The method involves receiving a target user's message in a social conversation; routing the message to a first social bot that outputs a clarification prompt and obtains a first response; if the first response does not provide verifiable information that meets preset verification criteria, subsequent messages are routed to a second social bot that outputs a specification prompt and obtains a second response; if the second response does not restate the request within the discussion boundaries as specified in the specification prompt, subsequent messages are routed to a third social bot that outputs a governance consequence prompt and obtains a third response; if the third response still does not meet the verification criteria or still does not restate the request within the discussion boundaries, the target user is determined to be an abnormal user; and a routing constraint strategy bound to the determination is applied to subsequent messages. This achieves coordinated linkage between social bot dialogue routing and abnormal user identification, improving system processing efficiency and governance stability while ensuring social order.

The invention discloses a foot type robot cluster surrounding control method based on an interaction force matrix. The method mainly comprises the steps that a multi-foot type robot cluster system dynamic model is constructed; setting cluster hunting control tasks and targets in different task stages; establishing interaction force matrix models of different task stages; designing a cluster hunting control strategy based on an interaction force matrix; in the process of executing the task, the cluster robot performs dynamic role allocation; on the basis of the strategy, the foot type robot gradually completes formation of the expected encircling formation from the initial position, and then encircling tracking is completed and collision with obstacles is avoided. According to the method, the interaction force and the terrain acting force between the robots are dynamically modeled, and a dynamic role allocation mechanism is combined, so that high-robustness self-adaptive cooperative control can be realized, the terrain adaptive capacity of a cluster in an unstructured environment is effectively improved, and a key technical path is provided for large-scale application in a complex scene.

The application discloses a cluster robot cross-view cooperative perception method and system for aircraft manufacturing, builds a multi-robot cooperative perception platform, collects wide-range three-dimensional point cloud data through a laser radar, and combines with a motion capture system to realize real-time acquisition of robot poses; a cooperative detection dataset containing a training set, a verification set and a test set is constructed; a point cloud cooperative three-dimensional detection model of cross-view consistency space mapping is innovatively designed, contains three core modules of multi-agent feature extraction, cross-view feature fusion and cross-view consistency-difference feature reconstruction, multi-robot perception cooperation is realized through hierarchical feature interaction, a joint loss function is used to optimize model parameters, and finally, the effectiveness and generalization ability of the method in a complex industrial scene are verified on the verification set and the test set, and platform deployment is carried out. The adaptability and expression integrity of the system to a complex structure environment are improved, and multi-agent cooperative perception is more efficient and reliable.

To make it easier to embody swarm robots, we provide a swarm robot control system equipped with a system that provides tactile feedback to the operator. [Solution] Target position coordinates are set for multiple robots that can move freely within a set field. Each robot moves toward its target position coordinates. Feature points on the operator's body are detected, and a value equivalent to the amount of movement of the feature point's position coordinate is assigned to the corresponding robot's target position coordinates. This causes each robot to behave in a way that follows the corresponding feature point. When the robots come into contact or collide, this is detected, and modules attached to the feature points corresponding to the robots output force, vibration, movement, or a combination of these, providing tactile feedback to the operator.

The invention discloses a bionic ant colony robot additive construction technology and system based on calibration dice space constraint, and relates to the technical field of intelligent construction, the bionic ant colony robot additive construction technology comprises the following calibration dice additive construction core steps: step 1, system initialization and global positioning, step 2, calibration dice setting and number recording, step 3, visual identification and local fine calibration, and step 4, calibration dice additive construction. According to the method, a calibration dice component, SLAM + UWB + visual identification multi-source fusion positioning technology is introduced into a bionic ant colony building robot system, and a closed-loop control mechanism of'simultaneous printing, identification and calibration 'is combined, so that the system realizes high-precision, autonomous and continuous in-situ building in a complex and unstructured environment; compared with existing building printing equipment, the building printing equipment has the remarkable advantages in the aspects of positioning precision, building stability, environmental adaptability, multi-machine cooperation efficiency, structural integration and the like.

The application discloses a completely distributed state observation method with a time convergence, and belongs to the technical field of multi-agent system cooperative control and state estimation. The application solves the problems that the existing method needs to depend on global network topology information and cannot realize controllable real convergence time and poor robustness. The application can make each follower independently and efficiently reconstruct the state and derivative of a leader which cannot be directly obtained without any global network information, and ensure that the estimation error accurately converges to zero within the real time set by a user. Moreover, the state observation method of the application is suitable for dynamic systems with external disturbance and model uncertainty, has good robustness and engineering application prospect, and is suitable for application scenes, such as spacecraft formation, unmanned aerial vehicle cluster and robot cooperation, which need high-precision synchronization and robustness. The method of the application can be applied to multi-agent system cooperative control and state estimation.

A kind of cluster robot cooperative operation method and system based on hierarchical path planning, wherein the cluster robot cooperative operation method comprises: the spatial partitioning of the environment map of cluster robot operation is carried out, and a plurality of unobstructed cells are obtained;Improved RRT* algorithm is used to preliminarily plan the path of cluster robot, and heuristic function is combined to guide the expansion of tree structure to target cell boundary;The path conflict between multiple measurement robots is coordinated using CBS algorithm, and a collision-free path set is formed;CBS algorithm is used to uniformly plan the path for one or more tracking robots;The path of all measurement robots and the path of each tracking robot are respectively subjected to path smoothing processing, and the final planned collision-free path is obtained.The present application can significantly improve the path planning efficiency and target orientation by dividing the operation environment into bounded cells and combining improved RRT* algorithm to sample at cell boundary.

The present invention relates to a distributed fault detection method in a swarm robotic system based on machine learning, belonging to the field of robotic control and fault detection technology. This method aims to address the single point of failure problem inherent in centralized fault detection by implementing fault detection and decision-making through a distributed architecture. Specifically, it includes steps such as information collection, feature extraction, machine learning classification, communication sharing, and voting. It utilizes a machine learning classification algorithm to improve fault detection accuracy, and uses a weighted majority voting mechanism to reduce misjudgments and enhance system robustness and fault tolerance. This method can be widely applied to fault detection and collaborative work in swarm robotic systems in complex environments.