1100 results about "Workspace" patented technology

Technology is described for determining a task plan that is usable by a robotic device in a workspace. The method can include converting instructions received for the robotic device into temporal logic (TL) statements and to a non-deterministic Buchi Automaton. A task probabilistic machine learning model can be generated with feasible task plans using the non-deterministic Buchi Automaton. A plurality of task plans can also be created or generated using the task probabilistic machine learning model. A sensor probabilistic machine learning model of the workspace can be constructed using information from sensors of the robotic device. The task plans from the task probabilistic machine learning model can be compared with the sensor probabilistic machine learning model to select the task plan with a high probability of correlation to the workspace.

The present disclosure relates generally to robotic systems, and more specifically to systems and methods for specifying a robot task configuration by means of annotating a visual workspace representation in coordination with a waypoint optimization process. This system enables a much broader use of robotic automation by saving time and reducing technical complexity. This system can be used to configure any visually enabled robotic task, such as tasks in warehouse management, manufacturing, delivery, inspection, logistics, etc.

A technique manages computing resources on a container orchestration platform. Such a technique involves establishing a pool of computing resources on the container orchestration platform. Such a technique further involves, after the pool of computing resources is established, receiving graphics processing unit (GPU) provisioning requests (GPRs) which identify workspaces. Such a technique further involves allocating computing resources from the pool to the workspaces identified by the GPRs based on a set of GPR prioritization policies.

A mobile track safety device (1.1), in particular a track worker warning system, for securing a work area (2) on a track section (3.1, 3.2) comprises a signal processing unit (19) for processing digital information, wherein the signal processing unit (19) has at least one interface (6) for receiving a position of at least one moving hazard object (8, 12), in particular a rail vehicle (12), from a tracking device (13.2, 17), and for receiving a position of at least one moving protection object (8, 16), in particular a track worker (16), from a tracking device (13.2, 17) and for issuing a safety command to secure the work area (2), wherein the signal processing unit (19) is configured to determine a hazard potential by comparing the positions of the at least one hazard object (8, 12) and the at least one protection object (8, 16) and to issue the safety command via the interface (6) depending on the determined hazard potential. A method for securing a work area (2) on a track section (3.1, 3.2), in particular by means of such a track safety device (1.1).

The invention discloses a mechanical arm teleoperation control method and system based on incremental mapping, and the method comprises the steps: carrying out the noise reduction processing of the position and posture of a handle through adaptive low-pass filtering, and achieving the position and posture consistency mapping from a handle space to a mechanical arm working space after coordinate system axis rearrangement and similar transformation mapping; the system provides two kinds of control output of a pose tracking mode and a speed tracking mode, real-time inverse kinematics solution is carried out through a Jacobian matrix and a damping least square method in the speed mode, and resolution scaling and exponential moving average / spherical linear interpolation smooth filtering are carried out on a target pose in the pose mode. And then the handle motion instruction is mapped into a Cartesian instruction or a joint space instruction at the tail end of the mechanical arm, closed-loop execution is conducted through a real-time state feedback link, and the method can be used for scenes such as robot service, teaching, remote operation and data collection.

Robot calibration is crucial in multi-robot cooperative systems where the inaccuracy of robots can add up and cause large errors in the final trajectory of handled parts or process tools. In this work, a two-step calibration approach is proposed based on artificial neural networks (ANNs) and definition of compensated pose for a master-slave cooperative robot system. Measuring the pose of master and slave robots at different locations in their shared workspace is required to create pairs of joint angles and output pose errors as training data. The generated data is used to train two ANN models for compensating the master-slave relative error and the master robot errors. The master-slave relative error is corrected by introducing a compensated pose for the slave robot with respect to the master robot. A neural network is then trained to predict the error parameters of the compensated pose for the joint angles of both robots as the input. The master robot is then corrected individually using another ANN model to address the absolute accuracy of the cooperative system.Measurements and simulations have been performed on a dual-robot cooperative system before and after geometric calibration. The process of cross validation is carried out to find the best network architecture for the optimal performance in correcting the robots'errors. It has been shown that even after pre-existing model-based calibration of each robot, both the absolute accuracy of the master robot and the relative tracking accuracy can be further improved by the proposed implementation of ANN calibration.

The invention provides an industrial operation area multi-view video collaborative analysis method and system based on artificial intelligence. The method comprises the following steps: firstly, acquiring multi-view video data; secondly, based on the working area and the equipment layout, deducing a semantic association relationship among the multi-view video data; according to the semantic association relationship, dynamically adjusting the analysis priority of the multi-view video data through an artificial intelligence model to determine an analysis priority sequence; and according to the determined analysis priority sequence, executing interactive co-processing of the multi-view video data, and finally generating a co-analysis result. According to the technical scheme provided by the invention, the physical layout and the workflow of the industrial site are converted into the semantic association relationship, and the dynamic scheduling analysis resources and the interactive collaborative analysis are performed according to the semantic association relationship, so that the spanning from simple monitoring of a plurality of isolated video streams to intelligent and coherent understanding of the whole operation flow is realized; and the intelligent level and decision support capability of monitoring analysis are improved.

The invention discloses an automatic high-precision assembly system and method based on visual feedback, belongs to the technical field of automatic assembly, and solves the problem that an existing scheme is insufficient in the aspects of automatic integration and actual usability. Comprising an embedded control unit, an XYZ Cartesian sliding table, a limiting sensor, a visual sensor, a visual mark and an upper computer processing unit, the embedded control unit is connected with the upper computer processing unit, and the embedded control unit is used for receiving a control instruction and feeding back state information. The embedded control unit is connected with a motor driver of the XYZ Cartesian sliding table and used for sending a motion control signal, and the embedded control unit is connected with the limiting sensor and used for receiving a switch signal. Working space boundary recognition and automatic calibration of the camera-robot hand-eye relation are achieved, the configuration and deployment process of a visual guidance system on the XYZ sliding table is greatly simplified, the requirement for professional skills of operators is lowered, and deployment efficiency is improved.

To provide a game machine provided with a program of a smaller size capable of initializing a main RAM respectively relating to a work area inside a use area and a work area outside the use area.SOLUTION: A RAM initialization program determines the head address of a RAM initialization range relating to a work area inside a use area corresponding to the state of the game machine and determines the head address of the RAM initialization range relating to the work area outside the use area corresponding to the state of the game machine on the basis of the head address determined in such a manner.SELECTED DRAWING: Figure 205

The invention provides a landslide hidden danger identification method and device based on three-dimensional geometrical morphological characteristics of a slope flat section and a machine learning model, and a storage medium, and relates to the technical field of landslide hidden danger identification. Comprising the following steps: acquiring plane geometric characteristics and section geometric characteristics of a slope unit based on a slope unit main sliding surface and a main section of a historical landslide disaster or a known landslide hidden danger point in a target working area; standardizing the high-dimensional slope geometric feature data to obtain a corresponding high-dimensional geometric feature vector; inputting the sample set into the trained auto-encoder model, outputting a corresponding reconstructed feature vector, and determining a discrimination threshold; inputting the high-dimensional geometric feature vectors corresponding to all to-be-identified target slope units extracted in the target working area into the auto-encoder model, calculating through the auto-encoder model to obtain corresponding reconstruction errors, and determining potential landslide hidden dangers; and isolated misjudgment units in potential landslide hidden dangers are eliminated. By adopting the identification method provided by the invention, the landslide hidden danger can be rapidly and accurately identified.

The utility model provides a desktop type multidirectional adjusting polisher for polishing a steel cord wire rod. The desktop type multidirectional adjusting polisher comprises a base, an adjusting moving rod, an angle adjusting mechanism, a deviation rectifying mechanism, an operating platform and a driving mechanism. The driving mechanism, the adjusting moving rod and the deviation rectifying mechanism are mounted on the base; the angle adjusting mechanism is installed in the direction of the first end of the adjusting moving rod. A connecting supporting plate is fixed to the front end of the adjusting moving rod in the first end direction, and an operation platform is fixed to the upper surface of the connecting supporting plate. The abrasive belt is sleeved on the driving wheel and the three driven wheels of the driving mechanism, and the motor drives the driving wheel to drive the abrasive belt to polish the fracture of the wire rod. The angle adjusting mechanism is installed on the side face of the front end of the adjusting moving rod and used for adjusting the angle of the limiting baffle to be perpendicular to the operation platform, and the working area of the abrasive belt is perpendicular to the operation platform; the deviation rectifying mechanism is installed on the upper portion of the installation frame and used for adjusting the abrasive belt to be centered, and deviation rectifying fine adjustment of the abrasive belt is achieved.

A method for calibrating a sensor and projector with respect to a work area, the method including positioning a projector to project light indicators at locations in the work area and positioning a sensor with respect to the projector such that the sensor's field of view includes a selected portion of the work area. The sensor captures video or encoded data of activities at the work area. The sensor and projector are aimed at a set of coordinates upon the work area and the associated aim-point coordinates of the sensor and projector are recorded. The sensor and projector are aimed at additional sets of coordinates upon the work area, and the associated aim-point coordinates are recorded until a sufficient quantity of aim-point coordinates have been collected to form a calibration data set sufficient to calibrate the sensor and projector to the work area.

The application relates to a dexterous hand self-adaptive grasping method, a dexterous hand control system and a storage medium, the dexterous hand self-adaptive grasping method comprising the following steps: acquiring multi-modal perception data; after processing point cloud data to generate a point cloud global feature vector corresponding to a grasping target, mapping tactile patch information to a dexterous hand workspace to generate a simulated tactile signal; processing the point cloud global feature vector and the simulated tactile signal by using a Glow-CVAE conditional generation model to generate a candidate grasping gesture set comprising joint posture and pose parameters; determining the stability corresponding to each candidate grasping gesture, selecting a target grasping gesture from the candidate grasping gesture set according to the stability, and grasping the grasping target by using the target grasping gesture. Through the application, the problem that the adaptability to special-shaped parts and flexible objects is limited and the grasping stability is not high in the related art is solved, and the beneficial effects of high adaptability and stability of grasping diversified articles in a complex scene are achieved.

A system includes proximal and distal structures and a processor system. The processor system determines a first commanded motion of the proximal structure; determine a second commanded motion for joint(s) of the distal structure or an imaging device, wherein when the first and second commanded motions are performed in conjunction, a field of view of the imaging device is maintained relative to a workspace; and in response to determining that driving the joint(s) in accordance with the second commanded motion would cause the distal structure or the imaging device to violate a constraint: determines an alternate commanded motion for the joint(s) to maintain a defined geometric relationship between a first geometric feature fixed relative to the imaging device and a second geometric feature fixed relative to the workspace, drives the proximal structure in accordance with the first commanded motion, and drives the joint(s) in accordance with the alternate commanded motion.

The embodiment of the invention discloses a literature interpretation method and device based on multi-Agent collaboration, a medium and a program product. The method comprises the following steps: performing feature extraction on a target document, generating a document feature vector, screening a target processing template matched with the target processing template from a preset processing template set, and constructing a directed acyclic graph by using the target processing template; key information of the target literature is extracted and stored in a shared work area; on the basis of the execution sequence of the directed acyclic graph, calling a corresponding functional agent to read input data from the shared working area, executing a processing task on the basis of the input data, and writing an execution result back to the shared working area; and after the execution of each functional agent is completed, outputting a literature interpretation report integrated by the execution results stored in the shared working area. According to the method, dynamic adaptation of a literature interpretation strategy can be realized through feature-driven dynamic scheduling and a multi-Agent cooperation mechanism, flexible expansion of system functions is supported, and the intelligent level and comprehensive efficiency of complex literature interpretation are greatly improved.

Provided are a method, system, and non-transitory computer-readable medium for real-time autonomous path planning for a robotic device. The method includes receiving data about the robotic device in a three-dimensional workspace, encapsulating objects in the environment of the robotic device including the robotic device, a target, and one or more obstacles in simulated robotic space, calculating a direction of movement for the robotic device according to three virtual forces including a virtual attractive force, a virtual repulsive force, and a virtual tangential force acting at least partially perpendicularly relative to the virtual repulsive force, mapping each virtual force in the three-dimensional workspace into torque vectors in the simulated robotic space at each joint, converting a sum of the torque vectors into one or more commands for the robotic device defining a path to reach the target, and sending the one or more commands to the robotic device.

The invention relates to the technical field of software configuration management, and discloses a monorepo-based multi-version control and management method, which comprises the following steps: receiving a version switching instruction containing a target global version identifier and an environment identifier; loading the physically isolated environment version configuration file from a preset path according to the environment identifier; a target configuration node corresponding to the target global version identifier is positioned in the configuration file, recursive branch information merging operation is executed based on inheritance attributes and branch attributes in the node, and a final branch configuration set containing all sub-module target states is generated; and traversing the final branch configuration set, and calling a version control tool to switch the working area state of each sub-module to the corresponding target sub-module version identifier. Through the environment isolation and increment inheritance model, the problems of version definition redundancy and environment confusion in a multi-module warehouse are solved, and accurate backtracking and atomization switching of sub-module states are achieved.

Disclosed in the present invention is an error self-calibration method based on a feature component for a parallel coordinate measuring machine. The method comprises: constructing a geometric error model of a parallel mechanism; measuring a feature component by means of a coordinate measuring machine, and then mounting the feature component within the workspace of a parallel coordinate measuring machine; performing data collection on the basis of a sphere‑center‑distance constraint and a sphere‑radius constraint, and correspondingly constructing an error equation based on the sphere‑center‑distance constraint and an error equation based on the sphere‑radius constraint; combining the error equations to obtain an error calibration model based on various feature constraints, using an LM method to identify, correct and substitute kinematic error parameters of the error calibration model, and repeating this process iteratively until kinematic error parameters no longer change, so as to obtain corresponding geometric error parameters of the parallel coordinate measuring machine; and on the basis of the geometric error parameters, compensating for an end pose error in the coordinate measuring machine caused by a geometric error. The present invention greatly improves the motion precision of a parallel coordinate measuring machine.

Systems and methods for migrating users and modifying workspace definitions of persona groups are described. In some embodiments, a memory storage device may have program instructions stored thereon that, upon execution by a workspace orchestration service, cause the service to: distribute a first workspace definition based upon a first persona group associated with a user to a client device operated by the user, where the user IHS is configured to instantiate a first workspace based upon the first workspace definition; and in response to a change in a productivity or security metric of the first workspace, determine whether to: (a) migrate the user to an existing second persona group, (b) create a third persona group and migrate the user to the third persona group, (c) modify the first persona group and migrate the user to the modified first persona group, or (d) identify a potential security threat.

The embodiment of the invention discloses a TFT-LCD backlight optimization method and device based on deep learning and a displayer. The method comprises the steps that inherent physical attribute features of a TFT-LCD backlight module are extracted, and inherent defect features are synchronously collected; associating and fusing the two types of features into a learning constraint, and inputting the learning constraint into a deep neural network model to complete feature adaptation; mining an association mapping relation between the physical defect characteristics and display picture backlight output parameters through learning constraint guide model training; retrieving a defect compensation mapping rule base based on the association mapping relation and the current display picture characteristics, and generating a backlight adjustment strategy adaptive to the current scene; state data of backlight driving units are collected to divide working intervals, distribution and adjustment strategies are disassembled, partition backlight optimization instructions matched with all the units are generated, application logic reconstruction of AI in the display field is achieved, hardware characteristics are actively adapted, inherent defects can be effectively compensated, the matching accuracy of backlight and display content is improved, and the display quality is improved. The display consistency is enhanced; and the driving efficiency is optimized.

A construction machine includes processing circuitry and a transmitter. The processing circuitry is configured to obtain information on a work area in an area surrounding the construction machine. The transmitter is configured to transmit the information obtained by the processing circuitry to another construction machine in the area surrounding the construction machine.

The invention provides an automatic software development system based on multi-agent cooperation, and the system comprises a demand analysis agent which is used for receiving a natural language demand input by a shared working area, generating a demand specification document containing an acceptance standard based on the natural language demand, and sending the demand specification document to the shared working area; the detailed design agent is used for receiving a demand specification document input by the shared working area, performing system design based on the demand specification document, generating a design specification document and sending the design specification document to the shared working area; the project development agent is used for receiving a design specification document input by the shared working area, performing code development based on the design specification document, generating an executable code and sending the executable code to the shared working area; and the shared working area is used for storing and forwarding the natural language demand input by the user and the output of the demand analysis intelligent agent, the detailed design intelligent agent and the project development intelligent agent. The development efficiency can be improved, the labor cost is reduced, and the software quality is improved.

The invention discloses a templated business process management method, and relates to the technical field of enterprise management.The method comprises the steps that repeatable task units in a business process are represented and packaged into function components capable of being configured in a draggable mode, combined arrangement is conducted in a visual working area template, and process construction is conducted from the development coding level to the development coding level; according to the technical scheme, the method sinks to a configuration level which can be understood by business personnel, in the step of creating the visual workflow template, when the working area templates bearing specific tasks are bound with process nodes, separation and standardized packaging of business logic and execution logic are achieved, and various working area templates are predefined through a graphical interface; the node function assembly can be quickly completed only by quoting the templates in the flow chart, the defect that each node needs to be independently developed or written in a traditional mode is overcome, and the core defects that in the prior art, flow construction is complex, the reuse rate is low, and the method excessively depends on technicians are overcome.

The invention relates to a method for determining the position and / or orientation of tools of construction machines in a construction area, comprising the steps of: attaching at least one stereo camera to at least one construction machine or to a movable carrier, such that the stereo camera can detect at least one detection region within the construction area, preferably a working region of the construction machine, providing at least one reference point, the position of which is known relative to a predefined 3D world coordinate system and which can be recognised in the images of the stereo camera, in the detection region of the at least one stereo camera, calibrating the at least one stereo camera on the basis of the detection of the at least one reference point and triangulation in order to ascertain a transformation between the 3D world coordinate system and a 2D image coordinate system of the at least one stereo camera, preparing a virtual digital 3D terrain model of the construction area by means of digital image processing, in particular stereoscopy, and image recognition on the basis of the detection of the construction area by means of the at least one stereo camera, and representing predetermined working positions and detected actual tool positions and / or actual tool inclinations of the tool of the at least one construction machine in the virtual digital 3D terrain model.

The described technology is generally directed towards automated development of machine learning pipelines. An automated framework can extract topics from a data science workspace such as a machine learning notebook, transform and annotate cells of the machine learning notebook to various machine learning pipeline stages, and orchestrate the machine learning pipeline stages in a workflow that can be deployed into production data infrastructures.

A lift device includes a chassis, a platform, a lift assembly coupling the platform to the chassis, an actuator, a sensor, and a controller. The platform supports an operator and defines a work area having a deck and railing. The lift assembly raises the platform relative to the chassis. The actuator can move the platform relative to the chassis or propel the chassis. The sensor provides data indicative of a position of the operator relative to the work area. The controller is configured to receive, from the sensor, data indicative of the operator exiting the work area. In response to determining that the operator has exited the work area, the controller determines, based on the sensor data, a direction of travel of the operator, and operates at least one of the lift assembly or the actuator to move the platform according to the direction of travel of the operator.

Some examples relate to optimizing energy efficiency associated with workspaces in a building. In one specific example, a system can execute a trained machine-learning model to generate a predicted activity pattern associated with a workspace in a building, the predicted activity pattern being a forecast of workspace activity associated with the workspace over a future time window. The system can, based on the predicted activity pattern, generate at least one control signal for at least one control system associated with the workspace. And the system can transmit the at least one control signal to the at least one control system, the at least one control system being configured to receive the at least one control signal and responsively adjust at least one environmental condition associated with the workspace from a first setting to a second setting.

A peripheral device workspace cloud orchestrator executing at an information handling system may comprise a hardware processor executing code instructions to define user experience categories for existing peripheral device workspaces identified by peripheral device workspace identification value and a list of peripheral devices operatively at identified locations coupled to user information handling systems acting as anchor nodes for the existing peripheral device workspace and to recommend setup, for each of the user experience categories, a number of reconfigured peripheral device workspaces needed to handle execution of user workloads for all enterprise users based on previously received telemetry measurements for each of the user information handling systems, wherein each of the user experience categories includes a telemetry reading describing a user workload pattern for an anchor node and a combination of peripheral device functional capabilities for the existing peripheral device workspace for handling the user workload.

A work management system is applied to a work area in which a predetermined work is executed by a worker and a robot. The work management system includes a control section configured to control the robot such that a specified operation set in advance is included in an operation by the robot executing the predetermined work, an information acquisition section configured to acquire work information indicating a presence or absence of the specified operation in at least one of an execution result and an execution process of the predetermined work, and an identification section configured to identify whether a work subject of the predetermined work is the worker or the robot based on the work information acquired by the information acquisition section.