170 results about "Robot manipulator" patented technology

A robotic surgical system includes a robotic manipulator configured to perform surgical procedures under direct surgeon control. A surgical camera system captures real-time intraoperative video. An external imaging interface receives multimodal imaging data, including preoperative and intraoperative data from at least one of magnetic resonance imaging (MRI), computed tomography (CT), ultrasound, and fluoroscopy. An artificial intelligence (AI module has a trained neural network and a deep learning model trained on multi-institutional annotated surgical datasets, The AI module is configured to execute one or more of: fuse acquired video and imaging data into temporally and spatially coherent anatomical visualizations; generate continuously updating overlays aligned with the surgical field, with segmented anatomical features; projected tissue boundaries, proximity indicators for instruments, and predictive deformation trends; provide dynamic predictive trend visualization indicating zones of future anatomical complexity or risk; register and align preoperative imaging data with intraoperative imaging data in real time; adapt overlay presentation in response to tissue deformation without actuating the robotic manipulate or; and passively augment visual feedback without initiating any autonomous actuation of surgical instruments.

A robotic system includes a robotic arm that interacts with an object during operation. It further includes a locking component that, during operation, locks a multi-position component in an operating position. Responsive to a triggering event, locking of the multi-position component in the operating position is released and the multi-position component moves away from its operating position, facilitating separation between the robotic arm and the object.

A method of programming an industrial robot (100), with a robot manipulator (110) and robot controller (120), comprises: recording movements of the robot manipulator during a demonstration-based robot programming session, for thereby obtaining a robot trajectory; acquiring a video of the robot programming session; and generating, on the basis of the robot trajectory and the video, a robot program (C) executable by the robot controller, wherein the robot program includes at least one motion command which is expressed in a first reference frame (0 1). The method further comprises capturing operator input data indicating a first object (151) in an image in the video. The generated robot program includes a command to identify a position of an object resembling the first object in a work area (150) of a robot which executes the robot program; and the first reference frame is defined with respect to the identified position of the object resembling the first object.

A computer-implemented method, apparatus and system is provided for robotic task completion from natural language requests. The method may include: receiving a natural language command, processing the natural language command with a generative large language model to extract an intent and associated context, creating a three-dimensional (3D) open-vocabulary semantic scene graph of the environment, associating the scene graph with the intent and associated context, creating, based at least in part on the scene graph, an execution plan comprising a sequence of actions to complete the natural language command, and generating executable code or tool calls corresponding to one or more actions in the sequence of actions, and controlling one or more robotic manipulators and / or actuators to perform one or more actions of the sequence of actions based on the execution plan.

A method of programming an industrial robot, comprising: recording movements of a robot manipulator during a demonstration-based programming session, to obtain a robot trajectory (301); using a natural-language model (171), parsing speech data describing the programming session into at least one robot parameter (305) value and annotating the robot trajectory with the robot parameter value; and, on the basis of the annotated robot trajectory (306), generating a robot program (307). The method further comprises: capturing a video (302) of the programming session; using a vision-enabled language model, VLM (172), generating descriptions (303) of movements of the robot manipulator which are visible in the video; and generating said speech data (304) on the basis of the descriptions of the robot manipulator movements.

A method for controlling a robotic manipulator according to a task comprises accepting a feedback signal including a sequence of multi-modal observations of a state of execution of the task. The multi-modal observations are processed with a neural network having a self-attention module with a hierarchically conditioned output to produce a skill of the robotic manipulator and an action conditioned on the skill. The neural network is trained in a supervised manner with demonstration data to produce a sequence of skills and a corresponding sequence of actions for the actuators of the robotic manipulator to perform the task. The method further comprises determining one or more control commands for the one or more actuators based on the produced action and submitting the one or more control commands to the one or more actuators causing a change of the state of execution of the task.

A robot manipulator has a base; an arm connected to the base via at least a shoulder joint; and a control system with a dynamic stability determination module. The dynamic stability determination module of the control system determines whether a dynamic stability criterion is met. If the dynamic stability criterion is met, the arm is responds compliantly to an applied force; and if the dynamic stability criterion is not met, the control system causes motion of the base in the direction of the applied force.

This invention provides a system and method for reliably interconnecting a native gladhand on a trailer with an AV truck, in which the gladhand can vary in placement and type on the trailer front. A visually guided robot manipulator arm accesses the trailer front. The arm includes an end effector assembly that is arranged to visually navigate to the gladhand and engage the gladhand by latching onto a gladhand using a connection tool that includes a hinged gladhand / wedge capture assembly and a pressurized clamping connection plate that selectively engages the trailer gladhand seal. The capture assembly is arranged to accommodate different gladhand geometries in latching thereonto. The connection tool includes a hinge that is spring-loaded in both a locked and unlocked bistable state, and sensors monitor the state. The system can include passive or active compliance elements that accommodate moderate misalignment between the engaged gladhand and the robotic arm / connection tool.

The present invention belongs to the field of robotics technology, specifically a constant force grinding method for complex surfaces of a robot based on force feedback. The method comprises the following steps: Step 1, collecting information of a six-dimensional force sensor through a robot controller; Step 2, introducing a fastest differential tracker in the self-disturbance rejection control; Step 3, forming an admittance control model by the robot and the environment to realize the outer loop control of the robot manipulator; Step 4, constructing a non-singular terminal sliding film control law to realize the inner loop control of the robot manipulator, thereby realizing the grinding of the curved workpiece surface. The present invention can improve the force tracking effect of the manipulator in a complex and unknown environment, thereby greatly improving the robot grinding accuracy.

A teleoperation system, including a robotic controller configured to translate a plurality of user inputs to a plurality of robotic control signals. A robotic manipulator, configured to operate separately from the robotic controller and to receive robotic control signals from the robotic controller, the robotic manipulator comprising a plurality of first joints and an end effector, wherein the robotic manipulator is configured to assume a plurality of poses, and wherein each respective pose of the plurality of poses corresponds to a respective configuration of the plurality of first joints. A feedback system, operatively coupled to the robotic manipulator, the feedback system configured to generate feedback information and transmit the feedback information to the robotic controller, wherein the feedback information includes information that indicates a current pose of the robotic manipulator, including the respective configuration of the plurality of first joints corresponding to the current pose of the robotic manipulator.

Described herein are sample collectors configured for use with robotic medical systems. A robotic medical system can include a medical instrument that can be inserted into a patient to capture a sample. A robotic manipulator can be engaged with the medical instrument and configured to operate the medical instrument; a sterile barrier can be used to separate a sterile field containing the medical instrument from a non-sterile field containing the robotic manipulator; a sample collector can include a receiver portion positioned in the sterile field and configured to receive the sample when a distal end of the medical instrument is retracted from the patient; and a connector coupled to the receiver portion and configured to attach to the robotic medical system. The robotic system can place the sample in the receiver portion.

The invention provides a multi-modal flow matching-based motion prediction method and device for a body-equipped robot, and relates to the technical field of intelligent robots, and the method comprises the steps: obtaining an instruction text, an image feature set collected by a robot, and a depth image set corresponding to the image features of all moments and positions; performing feature splicing processing and feature refining processing on the image feature set to obtain an image sequence feature set, and performing feature fusion processing on the depth image set based on the image sequence feature set to determine a target visual feature; text features in the instruction text are fused with target visual features, text visual modal feature information is determined, and based on the text visual modal feature information, motion of the robot mechanical arm is predicted, and motion pose prediction features are determined. According to the method, the accuracy of motion prediction of the body-equipped robot can be remarkably improved.

A feedback controller for controlling a robotic manipulator to perform a task is provided. The feedback controller comprises a memory configured to store a hierarchical reinforcement learning (HRL) neural network including (i) nominal control policy, and (ii) recovery control policy. The recovery control policy is trained based on a recovery policy reward to select a switch-to-nominal action to transfer control to the nominal control policy to perform the task. The recovery policy reward is dependent on a nominal policy reward for training the nominal control policy. The feedback controller further comprises a processor configured to iteratively execute the HRL neural network to select at least one of a nominal action based on the nominal control policy, and a recovery action based on the recovery control policy and to control the robotic manipulator to perform the task based on the selected action.

The invention provides a robot mechanical arm cooperative control method based on imitation learning. The method comprises the steps that a robot historical state data set is constructed, feature extraction is conducted on the robot historical state data set through an encoder structure, and potential feature representation is obtained; acquiring a color image and a depth image of a target operated by a to-be-predicted robot through a binocular camera, and performing feature extraction processing on the color image and the depth image through a mode classification module and a visual feature extraction network to obtain mode feature and visual feature vectors; and inputting the joint state information, the potential characterization, the operation mode features and the fused visual features into a decoder to obtain an action block prediction result, and performing weighted averaging on action blocks at a plurality of continuous moments based on a time sequence integrated weighting mechanism to obtain a continuous control track of the robot mechanical arm. According to the method, the problems of discontinuous multi-stage strategies and error accumulation in a traditional control algorithm are solved, and two-arm cooperative control with smooth action and stable task is realized.

The innovation of the robotic compliant actuator derives from the utilization of the series elastic actuation principle, coupled with the fundamentals in compliant mechanics. This actuator constitutes a dynamic and adaptable actuation framework wherein an elastic component is sequentially integrated with a motor and gearbox, resulting in compelling force-regulating attributes. This actuation concept has been specifically customized for robotic systems, particularly robot manipulators and legged robots, fundamentally transforming the manner in which robots engage with their surroundings, executing tasks demanding precision, adaptability, and safety. This compliant actuator introduces an ingeniously designed mechanical spring that assimilates a compliant mechanism within its elastic component, thereby endowing itself with additional benefits inherent to compliant mechanics. Additionally, another layer of compliant mechanism serves as an amplification means to detect spring displacement. This augmentation aptly exemplifies human-like force-regulation behavior, particularly in the realm of robotic applications.

The design relates to photographic robotic arm for capturing videos or images of products, people, or scenes from different angles, and may be configured as a robotic manipulator; the design is characterized by the ornamental shape and external configuration of the photographic robotic arm.

A robotic system includes an autonomous order picker lift truck configured to move within a commercial environment that includes commercial products supported by donor pallets; a robotic manipulator assembly positioned on a platform of the autonomous order picker lift truck; and a control system communicably coupled to the robotic manipulator assembly and the autonomous order picker lift truck. The control system is configured to perform operations including commanding the autonomous order picker lift truck to move to a particular donor pallet or shelf that is mounted on a rack assembly at or above a support surface of the commercial environment; commanding the autonomous order picker lift truck to move the platform to the particular donor pallet or shelf; and commanding the robotic manipulator assembly to pick a commercial product or a case from the particular donor pallet or shelf and place it on an order pallet or a receiving pallet.

A robotic system includes a robotic manipulator configured to manipulate an endoscope having a camera associated therewith and control circuitry configured communicatively coupled to the robotic manipulator. The control circuitry can be configured to receive an image depicting a field-of-view (FOV) of the camera associated with the instrument, detect an anatomical feature in the image, display a graphical interface that includes the image and a visual overlay indicating a location of the anatomical feature in the image, and track the anatomical feature based at least in part on determining that the anatomical feature is a target anatomical feature.

The present disclosure includes a method and apparatus for ink jet printing an exterior surface of a vehicle including a reversibly moveable crossbeam mounted above an open pit; a first track located above the reversibly moveable crossbeam, a first reversibly moveable monument including a first serial robotic manipulator including a first end effector defining a first end effector range of motion based on fully extended reversible movement of the first serial robotic manipulator; a second track located in the open pit beneath the reversibly moveable crossbeam; a second reversibly moveable monument coupled to the second pair of rails, the second reversibly moveable monument including a second end effector defining a second end effector range of motion based on fully extended reversible movement of the second serial robotic manipulator. The first end effector range of motion overlaps the second end effector range of motion.

The invention discloses an engineering machinery vehicle driving robot special operation manipulator which comprises a box body, an electric cylinder, a two-degree-of-freedom parallel five-connecting-rod mechanism and an operation handle clamping device, the electric cylinder is placed in the box body, two input ends of the two-degree-of-freedom parallel five-connecting-rod mechanism are respectively connected with the electric cylinder, and the two input ends of the two-degree-of-freedom parallel five-connecting-rod mechanism are connected with the operation handle clamping device. The operation handle clamping device is arranged outside the box body and connected with the output end of the two-degree-of-freedom parallel five-connecting-rod mechanism, and the operation handle clamping device can be connected with an operation handle of the engineering machinery vehicle to complete operation. The system can replace human drivers to complete high-risk operation tasks under the dangerous operation working conditions of engineering machinery vehicles such as bulldozers, loaders and mine clearance vehicles and multiple fields such as mines, nuclear power and emergency rescue, the risk of operators is reduced, the quick response capability is improved, and the working efficiency is improved. The technical bottleneck that unmanned operation is achieved on the premise that existing engineering equipment does not need to be changed is broken through.

The surgical robotic access system provides access for robotic instruments and / or actuators including the introduction, operation and withdrawal of such robotic manipulators into a body cavity without permitting the escape of pressurized fluid or gas. The surgical robotic access system also provides a multi-faceted range of movement without touching or effecting pressure on the opening in the patient's body cavity.

To improve performance of input to a robot manipulator by a user.SOLUTION: The sensor unit is designed to record an input variable applied to the robotic manipulator by the user manually guiding the robotic manipulator, wherein the input variable is a kinematic variable or a force and / or a moment. The sensor unit is designed to transmit the input variables to the computing unit, and the computing unit is designed to convert the input variables by means of a predetermined input variable mapping, wherein the input variable mapping defines a mathematical mapping of the input variables to coordinates of the graphical user interface or to settings of the virtual control elements.SELECTED DRAWING: Figure 1

Surgical systems and methods involving machine learning models to characterize tool interactions. A tool may be coupled to the robotic manipulator and configured to manipulate tissue. The sensing system measures a displacement of the tool, a speed of the tool, and an interaction force applied to the tool. A control system controls the manipulator to move the tool to interact with the tissue. In response to interaction of the tool with tissue over time, the control system obtains measurements of displacement, speed, and interaction force from the sensing system. The control system implements a machine-learned model for receiving and processing the measurements to estimate stiffness / damping parameters of the tissue, and evaluating variations in the estimated stiffness / damping parameters to generate a characterization regarding the tissue or tool interaction with the tissue. The control system controls the manipulator and / or the tool based on the characterization.

This system increases the number of processes that can be automatically annotated, saving labor, and also detects feature areas in images that are not normally detected during processing. [Solution] A robot control device is used, comprising: a coordinate calculation unit that calculates coordinates from data of an object and a robot manipulator in a simulation environment; a first learning model generation unit that generates a first learning model including data of a first estimated position of the object and the robot manipulator in the simulation environment using first teaching data including coordinates on a simulation image; a second learning model generation unit that generates a second learning model including data of a second estimated position of the object and the robot manipulator in real space based on second teaching data generated using data of the object and the robot manipulator in real space; and a robot control unit that controls the operation of the robot manipulator based on the data of the second estimated position.

Provided is a system and method for alignment of a robotic interface. The system includes an alignment device operable to connect to a robotic manipulator for moving the alignment device. The alignment device facilitates relative pose for positioning of the robotic manipulator with respect to an object. The alignment device includes a plurality of directional radio frequency identification (RFID) scanners. The object includes a target having a plurality of RFID tags including at least three RFID tags spaced in a triangular configuration to define a plane.

The invention provides a robot manipulator control method, device and equipment and a medium, and relates to the technical field of manipulator control, the method comprises the steps that according to obtained stress data of two hands of a robot, a trained neural network model is adopted, and the mass center position of a carried object is determined; on the basis of the double-hand force-moment balance condition, according to the mass center position, the grabbing point position of the carried object grabbed by the double hands of the robot is determined, and the double hands of the robot are controlled to grab the carried object; on the basis of a model prediction control technology and a control obstacle function technology, according to the obtained obstacle information, a collision-free translational motion track of the carried object and collision-free translational motion tracks of the two hands of the robot are generated; and according to the obtained translation acceleration when the two hands of the robot carry the carried object, the expected posture when the two hands of the robot carry the carried object is determined. According to the method, through logic connection among the steps, the defects of object grabbing, two-hand posture adjustment and obstacle avoidance links in the prior art are comprehensively overcome.

A remnant extraction tool includes a nosepiece assembly and a vacuum assembly. The nosepiece assembly engages with a robotic manipulator to adjustably align with an exit side of a workpiece during a drilling operation through the workpiece at a predetermined location. The drilling operation includes drilling performed by another robotic manipulator from a drilling side of the workpiece. The vacuum assembly is in fluidic communication with the nosepiece assembly and engages with the robotic manipulator to selectively apply a vacuum to the exit side of the workpiece via the nosepiece assembly and to collect remnants from the drilling operation. A robotic manufacturing system includes a machine drill tool and the remnant extraction tool. The machine drill tool engages with a first robotic manipulator. The remnant extraction tool engages with a second robotic manipulator. Methods for extracting remnants during drilling operations at robotic manufacturing systems are also disclosed.

The application discloses an output feedback control method for a mechanical arm against random jump interference, firstly establishes a discrete-time mechanical arm Markov jump linear system model, analyzes the discrete-time mechanical arm system model based on the Markov jump process, then designs a state observer and a measured disturbance observer, constructs a compound output feedback controller, estimates the system state to realize state feedback control, and finally guarantees the finite time boundedness and performance of the system through a Lyapunov method and linear matrix inequality technology. The application solves the problem of not considering the influence of the measured interference on the mechanical arm system in the prior art, thereby causing poor stability and control performance of the designed scheme.

This disclosure describes inspection tools and methods to inspect and maintain the interior of vent gas manifold channels. A magnetically-coupled probe, (e.g., a ball, cylinder, rectangular cube, or disc), is inserted inside the vent gas manifold channel. A magnetically-coupled head then magnetically drags the magnetically-coupled probe through the channels of the vent gas manifold. The inspection tool uses a sensor to monitor the position of the magnetically-coupled probe inside of the channel. If an obstruction is encountered, the sensor monitors local changes in one of more physical or electrical properties of the inspection tool and alerts an operator. The magnetically-coupled probe may be a steel bucket with sharp leading edges that detaches and scoops up the obstruction. A programmed robot manipulator arm or human operator may move the head across the surface of the vent gas manifold parallel to the channel.