34480 results about "Robot" patented technology

A federated distributed computational system enables secure biological data analysis and genomic medicine with enhanced oncological therapy capabilities. The system implements patient-specific tumor-on-a-chip analysis through microfluidic control systems and cellular heterogeneity preservation, while integrating fluorescence-enhanced diagnostics using CRISPR-LNP targeting and robotic surgical navigation. The architecture coordinates spatiotemporal analysis of gene therapy delivery through molecular imaging and immune response tracking, and implements bridge RNA integration with multi-target synchronization. Treatment selection is optimized through multi-criteria scoring and patient-specific simulation modeling. Each federated node contains a local processing unit for biological data analysis, privacy preservation protocols, and a hierarchical knowledge graph structure. The system implements cross-species genetic analysis, environmental response modeling, and multi-scale tensor-based data integration, enabling research institutions to collaborate on complex, large-scale biological analyses while maintaining strict data privacy controls.

The invention relates to the technical field of multi-modal data processing, and discloses a multi-modal sensor fusion inspection method and system, and the method comprises the steps: collecting the multi-modal original data of power equipment through a multi-modal sensor in an inspection robot, and constructing a feature vector set; performing adaptive weight calculation on the multi-modal sensor according to the feature vector set to obtain a sensor weight set; carrying out conflict identification and resolution on the multi-modal original data to obtain a fusion data set; performing abnormal feature extraction on the power equipment based on the fused data set to obtain an abnormal feature set; and carrying out routing inspection trajectory optimization based on the abnormal feature set to obtain a target routing inspection path sequence, and carrying out equipment state joint prediction in combination with historical equipment routing inspection data to obtain an equipment fault prediction result. And thus, more accurate equipment state joint prediction is realized.

A federated distributed computational system enables secure oncological therapy optimization through robotic integration. The system establishes a distributed graph architecture with secure communication channels connecting computational nodes, implementing encryption protocols for cross-institutional data exchange. Each node contains processing capabilities for fluorescence-guided imaging, uncertainty quantification, and expert knowledge integration while maintaining hierarchical knowledge graphs of oncological biomarkers, interventions, and outcomes. The system coordinates domain-specific knowledge through token-space communication and implements an advanced robotic integration system for surgical interventions using spatiotemporal tumor mapping, multi-modal fluorescence imaging, surgical robot coordination, and space-time stabilized mesh management. Key capabilities include wavelength-specific multi-modal fluorescence detection, combined epistemic and aleatoric uncertainty estimation, tensor-based data integration with adaptive dimensionality control, and light cone search for adaptive treatment optimization—all while maintaining strict privacy controls.

A robotic surgical system includes a surgeon consol coupled to a patient consol, and the patient consol coupled to surgical instruments. A surgeon computer is coupled to or at the surgeon consol that is coupled to to one or more surgical instruments. A robotic surgery control system includes an artificial intelligence (AI) system with one or more deep learning algorithms. A feedback loop monitors and collects data from the one or more sensors. One or more cameras provide feedback to the robotic surgical system, and are configured to provide images of an anatomical object in at least a two dimensional (2D) arrangements of pixels / Deep learning algorithms of the AI system distinguish different anatomical objects from the images.

The invention discloses a logistics robot path planning method based on multi-modal perception, and relates to the technical field of robot path planning. Laser radar, visual camera and IMU data are fused, and environment state feature vectors are generated through multi-modal data synchronization and space-time alignment; the method comprises the following steps: analyzing environmental semantics by using models such as PointPill and YOLOv8, extracting dynamic characteristics, and identifying obstacles; constructing a space-time risk field, searching a path by a space-time algorithm, converting path points into a continuous trajectory, and optimizing the continuous trajectory; deviation is evaluated in real time, dynamic re-planning is triggered, and multi-robot cooperation and environment semantic understanding are included. Through multi-mode perception fusion, hierarchical planning, multi-target optimization and a cooperation mechanism, the obstacle detection accuracy and the obstacle avoidance success rate are improved, the path planning time is shortened, the energy consumption is reduced, the multi-robot conflict is reduced, the task efficiency is improved, the environment semantic understanding and task adaptive ability is enhanced, and the method is suitable for scenes such as intelligent storage and the like and has wide application prospects. The automation level is improved.

The invention discloses a point cloud data rapid processing system based on 3D vision, and relates to the technical field of point cloud data processing. The binocular acquisition module generates an anti-interference high-precision point cloud; the preprocessing module is used for reducing noise and dimensionality and retaining key geometric features; the hierarchical feature extraction module fuses curvature weight and a non-maximum suppression strategy, and improves the robustness of an ORB algorithm in rotation, scale and noise scenes; the industrial scene segmentation module accurately separates stacked objects through normal vector clustering and a dynamic region growing algorithm, and secondarily verifies boundaries in combination with a lightweight semantic model; the two-stage registration module dynamically adjusts a threshold value based on error feedback to realize pose optimization from coarse registration to fine registration; the coordinate mapping module establishes a space mapping model through multi-attitude calibration and robot multi-axis linkage trajectory optimization. The problem that in the prior art, a 3D machine vision algorithm is high in time delay is solved, the real-time performance and rapidity of 3D model recognition and feature extraction are improved, and the efficiency requirement of industrial production is met.

The invention discloses a robot real-time potential safety hazard recognition system based on multi-modal sensor fusion, and particularly relates to the technical field of intelligent inspection and safety monitoring, the system comprises five parts of data acquisition, information fusion, behavior response, trajectory analysis and risk output, and the potential safety hazard recognition system is used for recognizing potential safety hazards through image acquisition, thermal imaging, gas concentration and temperature and humidity information. Carrying out numerical value normalization and feature extraction, identifying potential abnormity and generating early warning; triggering data enhanced acquisition and track recording in the target area, and constructing a space-time path model to analyze an abnormal evolution trend; and finally, outputting a potential safety hazard assessment result according to a risk level classification rule by combining the enhanced information and the trajectory features. According to the method, high-precision early warning is realized through multi-source data acquisition and normalization fusion, the local recognition capability is improved based on dynamic enhanced acquisition of a behavior response mechanism, an abnormal development trend is tracked by combining track evolution modeling, risk level assessment is output according to the abnormal development trend, and accurate recognition and dynamic management and control of hidden dangers are realized.

The invention belongs to the field of intelligent edge systems and privacy enhancement computing, and particularly relates to a privacy protection-oriented robot large model cloud edge end collaborative reasoning and federated learning system, which comprises a cloud server layer used for deploying a large-scale pre-training model and executing complex reasoning and global federated learning coordination; the edge calculation layer is used for deploying an intermediate layer model and executing local data aggregation, privacy protection processing and intermediate feature calculation; the terminal equipment layer is used for deploying a lightweight model and executing data acquisition, primary processing and lightweight reasoning; the federated learning framework is used for optimizing the model; the privacy protection module is used for integrating data localization, differential privacy, homomorphic encryption, secure multi-party computing and a block chain verification mechanism; the adaptive allocation module is used for dynamically adjusting computing resources. According to the method, the problems of privacy leakage risk, computing resource limitation, network delay, insufficient data isolation and the like of the traditional AI service in a robot scene are solved, and efficient privacy protection and data security isolation are realized.

The invention provides a teaching-free welding robot path planning system based on visual autonomous learning, and relates to the technical field of industrial welding, and the teaching-free welding robot path planning system comprises a pose compensation module which is used for arranging three infrared reflective mark points on the surface of a clamp base in an L shape, collecting original point clouds of the mark points and a workpiece by using a stereo camera, and preprocessing the point clouds; generating a pose compensation matrix based on the offset of the actual coordinate and the theoretical coordinate of the mark point, and outputting a de-noising point cloud data set and a compensation matrix; and the pose correction module is used for fitting a workpiece plane equation by adopting a random sampling consistency algorithm on the basis of the de-noised point cloud data set, acting a pose compensation matrix on the workpiece plane equation, correcting a pose error caused by clamp drifting, calculating a welding seam track end point coordinate and outputting a corrected welding seam pose parameter and a scanning pose instruction. According to the method, clamp drift can be compensated, weld joint poses can be corrected, three-dimensional features are extracted, a collision-free path is planned, and the welding precision, efficiency and automation degree are improved.

The invention relates to the technical field of target detection, in particular to a robot three-dimensional environment sensing method and device based on deep visual learning, and the method comprises the steps: collecting visual data based on a sensing system carried by a robot, carrying out the synchronous processing, extracting the spatial structure characteristics of a synchronous visual data stream and a preliminary semantic segmentation map, and carrying out the recognition of a target image; combining the spatial structure features with the preliminary semantic segmentation map to generate a geometric semantic feature map; extracting and optimizing local, regional and global features of the geometric semantic feature map, and performing three-dimensional modeling processing according to a multi-scale feature tensor to generate a three-dimensional geometric model; and carrying out fusion optimization on the structure information of the three-dimensional geometric model and the geometric semantic feature map, and carrying out verification processing based on a verification framework to obtain three-dimensional environment perception data. Through deep visual learning and visual data fusion, the defects of insufficient accuracy and limited deep semantic understanding ability in complex three-dimensional environment perception in the prior art are solved.

A structural-health-monitoring system is disclosed for real-time detection and autonomous maintenance of physical structures. The system includes a sensor network comprising at least one strain gauge and one tri-axial accelerometer mounted on the structure to generate real-time sensor signals. A perception module filters and normalizes the signals and extracts numerical features such as peak amplitude and dominant frequency. A digital-twin module maintains a finite-element model updated in response to the extracted features. A data-driven surrogate model predicts sensor behavior and refines itself using machine-learning techniques. An anomaly-detection module computes an anomaly score from model residuals or classifier outputs. Upon exceeding a threshold, a maintenance module initiates a maintenance action, including generating an inspection schedule or issuing a control signal to an autonomous inspection or repair device. A learning module continuously improves system performance using reinforcement learning based on historical outcomes. The system supports predictive diagnostics, robotic repair, and automated optimization for long-term structural integrity.

The invention discloses a monorail crane inspection robot intelligent test method based on data analysis, and relates to the technical field of intelligent detection, and the method comprises the following steps: synchronously collecting track images, point cloud and attitude data, carrying out time alignment and preprocessing, and outputting a standardized data packet; detecting an inspection target by using a YOLO detection network, and outputting a multi-scale feature vector in combination with a point cloud feature hierarchy extraction network and a time sequence convolutional network; predicting a fault development trend in combination with an improved A-star algorithm and a long short-term memory network, optimizing an inspection path through reinforcement learning, and outputting a maintenance decision scheme; the maintenance decision scheme is converted into a control instruction, the robot is driven to execute an inspection task and feed back the operation state in real time, incremental learning and point cloud reconstruction are combined, and a visual diagnosis report is output. According to the method, the dynamic threshold algorithm is adopted for self-adaptive analysis, and the key geometric indexes are calculated in combination with the cross-modal attention mechanism, so that the recognition capability of structural anomalies is improved.

In one implementation, a computer-implemented method involves receiving a user message corresponding to a query or a statement to AI chatbot, performing preprocessing operations resulting in generation of initial context of the user message by extracting text of the user message, metadata of the user message, and a conversation identifier, obtaining historical context pertaining to the user message from a plurality of storage mechanisms provided in differing formats including a knowledge graph, a vector database comprised of vector embeddings, and a database comprising text summaries of prior conversations between the user and the AI chatbot, generating a prompt for a LLM that instructs the LLM to generate a response to the user message that is based on and consistent with the user message, the initial content, and the historical context, and providing a final response to the user that is corresponds to an LLM-generated response.

The invention discloses a defect repair method based on digital twinning and friction stir welding technologies, and relates to the technical field of intelligent manufacturing and digital twinning, and the defect repair method comprises the following steps: synchronously capturing full-dimensional data of a welding area through a multi-mode sensor array integrated by an actuator; secondly, segmenting defect boundaries by adopting a deep learning algorithm, constructing a dynamic twin model in combination with thermal-force field coupling simulation, and accurately mapping defect three-dimensional features; generating a repair track according to the twinborn model, converting the repair track into a robot joint instruction through a curved surface parameterization mapping algorithm, and implanting real-time anti-collision constraint; in the repairing process, based on reinforcement learning control of the material rheological resistance and the temperature gradient, the rotating speed, the advancing speed and the down force of the tool are dynamically adjusted; and after repairing, micro-focus CT scanning is started immediately, actually measured data is compared with twinborn prediction, and when the deviation exceeds a threshold value, a re-repairing process is triggered automatically. The method solves the problems that a traditional method depends on manual intervention and the precision of a sensor is easily interfered by the environment.

The embodiment of the invention provides a swimming pool robot positioning and trajectory prediction method and system fusing sonar and vision. The method comprises the following steps: collecting terahertz sonar data for a target area; based on terahertz sonar data, constructing a motion track model of the swimming pool robot; acquiring multi-source image data by adopting a multi-spectrum and event camera collaborative acquisition strategy; a dynamic SLAM algorithm based on deep learning is adopted, dynamic objects in the swimming pool environment are recognized and processed in real time based on the multi-source image data, and the environment image data with the dynamic objects removed are adopted to obtain a swimming pool environment model; performing deep fusion on the motion track model and the swimming pool environment model through a knowledge graph network, and predicting the operation state of the swimming pool robot by adopting a quantum machine learning algorithm to obtain a panoramic model; and creating and updating a digital twinborn model corresponding to the panoramic model in real time. The real-time performance and accuracy of positioning and track prediction of the swimming pool robot are improved, and a user can conveniently maintain and manage the swimming pool robot.

The invention provides an intelligent storage robot group cooperative scheduling method based on deep reinforcement learning, and relates to the technical field of intelligent storage, and the method comprises the steps: constructing a group perception module through a hierarchical attention mechanism, and generating a dynamic cooperative perception matrix; establishing a deep reinforcement learning model for strategy learning; and designing a multi-level reward function and optimizing a training process through an adaptive weight adjustment mechanism. According to the invention, the cooperative efficiency of warehouse robot group scheduling is improved, the task conflict rate is reduced, and the adaptability of the system to a complex dynamic environment is enhanced.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes of robot strategy training, financial science and technology, medical treatment and health and the like, and discloses a strategy optimization method and device based on an interaction track, equipment and a medium. The reinforcement learning agent interacts with the environment to generate an action and state sequence and record an interaction track, an optimal action strategy is generated based on a track optimization strategy, an original empirical data set is further generated, and a pre-training model is optimized through supervised learning to obtain a target strategy model. According to the method, a task-related high-quality trajectory is generated through reinforcement learning agent and environment interaction, original empirical data is extracted on this basis, and a pre-training strategy model is optimized in combination with a supervised learning mechanism, so that the sample utilization efficiency is effectively improved, and the generalization ability and execution robustness of the model under a multi-task condition are enhanced.

The invention discloses a seabed tracked robot path planning method and system based on reinforcement learning, and the method comprises the steps: obtaining environment data in real time through multiple sensors, extracting submarine topography three-dimensional features, obstacle distribution and ocean current dynamic parameters in combination with a neural network, and carrying out the combined feature extraction; establishing a seabed environment simulation model, and synthesizing various landform training data by using an adversarial generation technology; a hierarchical reinforcement learning framework is designed, a global layer collaboratively optimizes a long-distance path through a distributed agent, a local layer designs a high-frequency control strategy, and the global and local strategies realize multi-dimensional collaborative optimization through a dynamic weight adjustment mechanism; model parameters in a dynamic environment are updated in real time through an online optimization module, and a simulation strategy is quickly deployed to an entity robot through transfer learning. According to the invention, a neural network feature extraction and multi-level reinforcement learning collaborative autonomous decision-making system is constructed, and a high-reliability and low-energy-consumption autonomous operation solution is provided for a deep sea operation scene.

The invention relates to a robot sensing and decision-making method based on a lightweight multi-modal large model. The method comprises the following steps: constructing a semantic voxel map; collecting multi-modal data based on the semantic voxel map and preprocessing the multi-modal data, wherein the multi-modal data comprises visual data, point cloud data and a target semantic tag; performing feature extraction on the preprocessed multi-modal data, and performing dynamic cross-modal attention fusion to obtain multi-modal fusion features; inputting the multi-modal data into a lightweight multi-modal large model at the same time, and performing semantic analysis to obtain global space object semantic description; and based on the global space object semantic description, the target and direction embedding vector and the multi-modal fusion feature, a reinforcement learning algorithm is adopted to carry out hierarchical navigation decision making to obtain a target decision, and the target and direction embedding vector is a preprocessed target semantic tag. And the accuracy, timeliness and adaptability of robot perception and navigation decision making in a complex scene are improved.

The embodiment of the invention discloses a database multi-source heterogeneous data synchronization method and device.The method comprises the steps that a data change event is monitored through an RPA robot deployed in a server where a source database is located, and when change operation of structured data or unstructured data is detected, an initial data set is generated; performing fragmentation processing on the initial data set to generate a plurality of data fragmentation tasks, and allocating the data fragmentation tasks to distributed computing nodes to execute parallel format conversion operation so as to generate a target data set; detecting a task execution state of the distributed computing node, and when a generation completion event of a target data set is detected, activating a data synchronization channel and transmitting the target data set to a target database; and performing conflict detection and identification based on an RPA conflict processing strategy configured in the target database, when a primary key conflict or a uniqueness constraint conflict is identified, updating the target database based on preset conflict merging indication information, and generating a data synchronization log.

The invention discloses a cable inspection robot attitude control method based on MPC and ADRC fusion, and the method comprises the steps: firstly, building a model prediction control (MPC) model, carrying out the prediction of the future state of a robot, solving an optimal control problem, and obtaining initial control input for achieving the internal dynamic compensation; secondly, an extended state observer (ESO) in an auto-disturbance rejection control (ADRC) model is adopted, and external disturbance is estimated in real time and used for compensating control input; thirdly, a fuzzy self-adaptive module based on fuzzy PID is introduced, the attitude error, the attitude error change rate and regeneration disturbance intensity generated based on estimation disturbance are collected in real time, the MPC weight and the ESO gain are dynamically adjusted, and the response speed and robustness of the system under variable working conditions are improved. According to the hierarchical control scheme, the defect that an existing single control method is difficult to keep the optimal control effect under variable working conditions is effectively overcome, and technical guarantee is provided for stable operation of the cable inspection robot in a high-risk and high-complexity environment.

The invention discloses a road bridge design method and system based on a BIM real scene model, and relates to the technical field of constructional engineering information, and the method comprises the steps: a BIM model carries out multi-objective optimization through a quantum annealing algorithm in combination with a bridge-crossing topology library, synchronously optimizes topological connectivity, structural stress and energy consumption indexes, generates a parameterized component, and feeds back the parameterized component to the BIM model; the model of the BIM model is loaded and optimized based on augmented reality equipment, the model is superposed to a reality scene through space anchoring, and the BIM model is corrected in combination with a conflict monitoring engine and a knowledge graph; the corrected BIM model is deployed to edge computer equipment, a dynamic deviation thermodynamic diagram is generated by scanning a construction surface, a lofting robot is driven to execute coordinate dotting, and meanwhile construction error data is transmitted back; according to the method, the problem that a global optimal solution is difficult to find when a traditional optimization algorithm is used for processing a complex multi-target problem is solved by utilizing an advanced quantum computing technology, and the economical efficiency and the structural safety of bridge design are greatly improved.

The invention provides an all-terrain autonomous navigation and task planning method and system for a photovoltaic inspection robot, and relates to the technical field of photovoltaic inspection, and the method comprises the steps: constructing a three-dimensional grid map and generating an initial inspection path, dividing hexagonal sub-regions and calculating a passing cost matrix, and optimizing a global inspection path based on the cost matrix. The motion state is predicted in real time, the motion track is corrected, thermal imaging and visible light data are collected to generate an inspection report, autonomous navigation and efficient inspection under complex terrains can be achieved, the inspection efficiency and accuracy are improved, and the labor cost is reduced.

The invention relates to the technical field of artificial intelligence, can be applied to the field of medical health, and discloses a navigation method, device and equipment in an unexplored environment and a medium. Analyzing a pre-trained large language model into a structured semantic representation at least comprising target entity information, spatial constraint information and contextual intention information; inputting the target entity into a pre-trained large language model to generate a standardized task description question, inputting the standardized task description question and real-time environment image data into a pre-trained visual language question and answer model, and outputting a semantic answer result about whether the target entity exists or not; and if yes, generating a navigation strategy through a pre-trained large language model based on the structured semantic representation, and controlling the robot to execute a navigation action through a preset path planning algorithm. The method does not need to depend on an environmental map and scene training, realizes navigation in an unexplored environment by utilizing cooperation of a large language model and a visual language question and answer model, solves the problem of strong dependency of a traditional scheme on prior data, and has good generalization ability and environmental adaptability.

The invention discloses a grabbing posture generation method and system based on a multi-modal large model, and the method comprises the steps: carrying out the cross-modal matching of visual features and semantic features in the multi-modal large model when a voice instruction and an RGB image are inputted, and obtaining the position information of a control function code and a target object; when an RGB image with a hand drawing instruction is input, obtaining position information of a control function code, a target object and a path point; calculating the point cloud data of the target object according to the position information of the target object and the depth information, inputting the ideal point cloud of the target object into a target recognition network model after preprocessing, carrying out the grabbing region recognition of the point cloud of the target object region, outputting a region with high grabbing confidence, and mapping a real coordinate system; constructing a point cloud bounding box, and generating a grabbing posture candidate set; the grabbing posture with the highest quality is selected as the grabbing posture of the robot by calculating the grabbing posture candidate score; and executing a target grabbing task in combination with the control function code and the grabbing path.

The invention relates to the technical field of robot anomaly prediction, in particular to a robot anomaly prediction method and system based on multi-dimensional fusion and causal inference. The method comprises the steps of performing multi-scale depth state characterization based on acquired robot multi-joint sensing data, and performing dynamic causal graph fusion based on the multi-scale depth state characterization. Comprising the steps of priori knowledge graph construction based on a kinematics chain, dynamic association attention mechanism construction based on data driving, state fusion of knowledge and attention guidance and global state vector generation. Performing hierarchical space-time dependency prediction based on the fused features, wherein the hierarchical space-time dependency prediction comprises robot joint topological graph construction, spatial dependency dynamic modeling, long-range time evolution prediction and future robot health state prediction; the method shows excellent performance in a plurality of core dimensions such as prediction precision, early warning timeliness and diagnosis interpretability, and has extremely high actual deployment value and engineering popularization potential.

The invention relates to the technical field of intelligent agricultural equipment, and discloses an automatic agaricus bisporus picking method, device and equipment based on artificial intelligence and a medium. The method comprises the steps that RGB images and three-dimensional point cloud data of the agaricus bisporus growth environment are collected in real time through a binocular vision camera and a depth sensor which are installed at the tail end of a picking robot, and environment illumination parameters and cultivation bed coordinate information are obtained; inputting the RGB image into a pre-trained lightweight convolutional neural network, identifying a pileus contour, a stipe position and a maturity level of the agaricus bisporus, calculating a space coordinate, a height and a growth inclination angle of the agaricus bisporus based on the three-dimensional point cloud data, and constructing an agaricus bisporus target database; a mechanical arm picking path is generated based on the agaricus bisporus target database, and path weight parameters are optimized online through a preset reinforcement learning model; according to the maturity grade and morphological characteristics of the agaricus bisporus, the clamping force and the rotating angle of the end effector are dynamically adjusted, and automatic picking of the agaricus bisporus is completed.

The invention belongs to the technical field of path planning, particularly relates to a robot dog inspection path planning method and system, solves the problems of poor operation endurance and inspection efficiency of a robot dog in a path planning method in the prior art, and comprises the following steps: S1, obtaining a three-dimensional grid map of an inspection environment; s2, generating an inspection point sequence; s3, sequentially planning each path section based on an improved A * algorithm, wherein the actual cost # imgabs1 # from the starting point of the path section to the current node # imgabs0 # is a scalar value integrating the path length, the traffic energy consumption and the equipment inspection information value; the heuristic cost # imgabs3 # from the current node # imgabs2 # to the end point of the path section is in direct proportion to the Euclidean distance from the current node # imgabs4 # to the end point of the path section; s4, when an obstacle is detected, performing dynamic re-planning of a local path; and S5, setting an optimal marching gait parameter for each terrain road section. And the path length, the passing energy consumption and the information value of the inspection point are comprehensively considered, so that the operation endurance and the inspection efficiency of the robot dog are improved.

An example operation may include one or more of executing an interaction with an account device about a first topic of interest and a chatbot within a chat element, wherein the interaction comprises an exchange of content between the account device and the chatbot within the chat element, receiving an interaction data from the account device within the chat element; determining that the interaction data is a second topic of interest based on an execution of an artificial intelligence model on the interaction and the first topic of interest, generating a chatbot response to the interaction data based on the execution of the artificial intelligence model on a state of the interaction prior to receipt of the interaction data, and outputting the chatbot response within the chat element.

The invention discloses a robot unstacking grabbing pose estimation method based on an image segmentation model, and relates to the technical field of image processing, and the method mainly comprises the steps: taking a two-dimensional detection frame as a positioning basis, inputting an image segmentation model, generating a pixel-level mask of a grabbing target, mapping the pixel-level mask to a three-dimensional point cloud which is registered with the pixel-level mask, and carrying out the positioning of the three-dimensional point cloud; extracting a point cloud subset of the captured target according to a mapping result; normal vector estimation and direction consistency processing are carried out on the point cloud subsets, and division of point cloud clusters corresponding to each independent surface of the grabbing target is carried out by taking direction consistency as a clustering segmentation basis; calculating the mass center position of each independent surface of the grabbed target according to the divided point cloud clusters, and extracting a local point cloud within a preset radius range of the mass center; and the average point of the local point cloud serves as a grabbing point, the average normal vector of the local point cloud serves as the grabbing direction, and the grabbing pose of the robot is generated. According to the invention, when the object is inclined, stacked tightly or shaped irregularly, the point cloud subset mapped by the mask can still accurately eliminate the interference of the background and the adjacent object.