43 results about "Joint spaces" patented technology

The invention provides a training method and device for a VLA model, and relates to the technical field of intelligent robots with bodies, and the method comprises the steps that the VLA model outputs a joint angle sequence of a mechanical arm of a robot with a body based on visual input and language input; the differentiable forward kinematics module outputs a real-time pose of an end effector of the mechanical arm in a task space; based on joint space loss formed by the joint angle sequence and the joint angle in the teaching data, task space loss formed by the real-time pose and the tail end pose in the teaching data, and task space constraint loss, a multi-objective loss function is constructed, and total loss is calculated; calculating the gradient of the total loss to the joint angle sequence and the real-time pose through back propagation, and optimizing preset parameters of the VLA model; the above steps are repeatedly executed until the total loss meets the expectation, and a trained target VLA model is obtained; the technical problems that when a VLA model is trained in a joint space, the hardware coupling performance is high, and the generalization ability is insufficient are solved.

The application relates to a multi-arm mobile robot control system, which comprises a robot, each joint position of the mechanical arm of which is configured with a joint controller for driving joint movement; a robot controller for realizing the operation of joint motors according to control quantities; a joint position hard analysis unit for calculating the coordinate positions of each joint or mechanical arm in a space coordinate system to output results; and a joint space point position trajectory constraint model for forming a correction quantity of a joint and superimposing the correction quantity on an original control quantity of the joint to become a final control quantity for controlling the joint, the final control quantity being used for output to the joint controller to realize joint movement. The application provides a multi-arm mobile robot control system, which effectively realizes the cooperative control among multi-arm robots, avoids the mutual collision among mechanical arms, improves the avoidance and dynamic response speed of the mechanical arms, and improves the agility of robot actions.

The invention belongs to the technical field of robot intelligent control, provides a robot double-source joint information impedance control method and system, a medium and a robot, and aims at motion control of a 3R-configuration robot. Joint motion information including a filtering angle, a filtering angular velocity and a filtering angular acceleration is obtained, the pose and / or velocity information of the end effector is mapped to a joint space based on a kinematic model of the robot, and joint motion information including a mapping angle and a mapping angular velocity is obtained; fusing the angle and the angular velocity to obtain a fused angle and a fused angular velocity; and generating a control torque by combining the fusion angle, the fusion angular velocity and the filtering angular acceleration with a preset target impedance parameter and an expected trajectory. The angular velocity and the angular acceleration can be obtained without adding velocity and acceleration sensors on the motor, and the increase of the size, the complexity and the cost of the joint control motor is avoided.

The invention relates to the technical field of medical image auxiliary diagnosis, and provides an intervertebral joint osteoarthritis image feature evaluation method based on deep learning, which can synchronously identify five types of FJOA image features such as joint space stenosis, osteophyte, hypertrophy, subchondral bone erosion and subchondral cyst, and improves the comprehensiveness and efficiency of evaluation. The nnU-Net model is adopted to perform high-precision segmentation on an intervertebral joint region, so that the positioning precision is effectively improved; by introducing a shared feature extraction network based on ResNet-18 and five parallel classification sub-networks, joint modeling of multi-scale semantic information is realized, and the recognition accuracy and generalization ability of the model are improved; according to the method, a Grad-CAM technology is combined to generate an activation thermodynamic diagram, a model interpretation basis is superposed to an original image, visual display of an evaluation result is realized, interpretability and clinical applicability of the model are enhanced, and FJOA image features in axial lumbar vertebra CT images from two central data sets can be quantitatively evaluated so as to comprehensively quantify individual FJOA image features.

The invention provides a mechanical arm control method and device, computer equipment and a storage medium, and the method comprises the steps that the target tail end pose and the initial joint angle of a mechanical arm are obtained; based on the target tail end pose, self-motion variables are introduced to parameterize the joint space of the mechanical arm, and multiple sets of candidate joint angles are obtained; constructing a joint motion cost function, and determining the total cost of moving from the initial joint angle to each group of candidate joint angles based on the joint motion cost function; traversing the value range of the self-motion variable, and screening out a solution with the minimum total cost from the multiple groups of candidate joint angles according to the joint motion cost function to serve as an optimal inverse kinematics solution; and a control signal is generated based on the optimal inverse kinematics solution, all joints of the mechanical arm are driven to move, and therefore the tail end of the mechanical arm reaches the target tail end pose. By the adoption of the method, the accuracy, economical efficiency and reliability of mechanical arm control can be improved.

An intraoperative surgical system for knee arthroplasty may be configured and / or reconfigurable to allow the surgical system to be inserted into different sized joint spaces during a surgical procedure. For example, the surgical system may include a sensor support body defining a platform, a force sensor, and a plurality of sensor covers each being configured to be detachably attached to the sensor support body. Each of the sensor covers can vary from each other in at least one characteristic. A selected one of the sensor covers can be placed over the platform, sandwiching the force sensor between the platform and sensor cover, to define a joint insertion block configured to be inserted into a tibiofemoral joint for measuring a force between a tibia and a femur defining the tibiofemoral joint.

The invention discloses a flexible wiping method and system of a flexible joint space robot based on dynamic adaptive impedance control, and the method comprises the steps: firstly, building a contact model between the flexible joint space robot and a wiped target; then, self-adaptive impedance control for dynamically updating impedance parameters is designed; and finally, performing comparison simulation on classical constant impedance, fixed update rate adaptive impedance control and dynamic update rate adaptive impedance control, and verifying the effectiveness of the method combining the dynamic update rate adaptive impedance control and singular perturbation control on friction force compliance control in the wiping process of the flexible joint space manipulator by a simulation result. The method is used for the field of on-orbit wiping of the flexible joint space robot, and accurate compliance force control can be conducted on the flexible joint space robot rapidly, efficiently and accurately; when the flexible joint space robot executes a task, necessary guarantee can be provided for the flexible joint space robot, and it is ensured that the space robot and a wiping target are not damaged, and meanwhile a good cleaning effect is obtained.

The invention discloses a characterization method for describing tibia malformation correction path features, and the characterization method comprises the following steps: S1, building a bone section model, and modeling a bone section after osteotomy into a closed ring surface with the tail end of the bone section as the center; s2, according to the total correction period, the total adjustment amount of all traction rods of the parallel external fixator is averagely distributed every day, and then joint space equal-interval discrete planning is achieved; s3, constructing correction path characteristic evaluation indexes including rod length adjustment rate, bone section position stretching rate and bone section posture stretching speed; s4, the new bone shape is visually represented, the growth process of the bone section is represented as a series of discrete closed ring surfaces along the correction path, and the new bone shape is represented as the volume swept by the series of discrete closed ring surfaces along the correction path. According to the method, the visual representation of the new bone generation process in the malformation correction process is realized, so that a clinician is assisted to carry out feasibility analysis and evaluation on a preoperative correction prescription.

The invention discloses a knee joint force line adjusting system and method based on intelligent feedback control, and relates to the technical field of medical rehabilitation instruments. The system comprises an overall control and man-machine interaction end, a correction device sensor end and a correction device hardware platform end. The hardware platform end comprises a joint force applying module and a thigh and shank multi-degree-of-freedom motion module; the sensor end is used for detecting joint pressure and lower limb force line state in real time. On the basis of traditional three-point type orthopedics, the applied force is adjusted through the control module according to real-time feedback, and the shank is matched for synchronous stretching and rotating movement, so that the knee joint force line is dynamically adjusted. In addition, the system combines multi-modal data, constructs a closed-loop decision model by using deep learning and large model reasoning technologies, and outputs correction effect evaluation and next training parameter recommendation. The digital and intelligent knee joint correction system realizes digitization and intelligentization of knee joint correction, can effectively enlarge joint gaps, improves stress distribution, and provides a personalized and safe rehabilitation treatment scheme for middle-aged and elderly osteoarthritis patients.

The application belongs to the technical field of robot intelligent control, and provides a robot dual-source joint information impedance control method, system, medium and robot, which is oriented to the motion control of a 3R configuration robot, and comprises the following steps: performing signal filtering and differential processing on original motion state data of each joint of the robot to obtain joint motion information including filtered angle, filtered angular velocity and filtered angular acceleration; based on a kinematics model of the robot, mapping pose and / or velocity information of an end effector to a joint space to obtain mapping angle and mapping angular velocity; respectively fusing the angle and the angular velocity to obtain fused angle and fused angular velocity; and generating a control torque by combining the fused angle, the fused angular velocity and the filtered angular acceleration with preset target impedance parameters and an expected trajectory. According to the application, the angular velocity and the angular acceleration can be obtained without adding speed and acceleration sensors on the motor, so that the size, complexity and cost of the joint control motor are avoided.

The invention relates to an articulated robotic arm device with a neural-network system for movement of a robotic arm, the neural-network system being capable of learning online and in real time the forces for moving its joints towards a target position by simulation of virtual springs implementing impedance control, wherein learning the rest elongations of the virtual springs for a selected state defines the equilibrium position of the arm corresponding to a zero resultant of the forces applied to the arm, thereby giving the arm elasticity properties as a function of the stiffness selected for the springs, at equilibrium, wherein the neural network learns these elongations for each transition from one target position to another target position in the joint space, making it possible to control movement of the arm in order to learn a sequence of movements and define the behavior of the arm for a given task, each joint of the arm having a target position.

The application relates to an environment perception-based mechanical arm obstacle avoidance trajectory planning method and system, which comprises the following steps: acquiring joint angle data and end effector position data of a mechanical arm, establishing a joint space for mechanical arm work according to the joint angle data and the end effector position data; acquiring environment point cloud data, extracting obstacle information based on the environment point cloud data, and acquiring a safe operation space of the mechanical arm through the obstacle information; acquiring a current joint angle combination of the mechanical arm, converting a position difference between the current joint angle combination and a target position into an angle increment in the joint space, and adjusting an angle value exceeding the boundary of the safe operation space, so as to complete obstacle avoidance trajectory planning of the mechanical arm. The application can realize a grabbing task while avoiding obstacles.

The application relates to a robot motion trajectory determination method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring a given joint position waypoint, determining a first transition waypoint between a current joint position waypoint and a previous joint position waypoint, determining a second transition waypoint between the current joint position waypoint and a next joint position waypoint; creating a joint position spline path according to the given joint position waypoint, the first transition waypoint and the second transition waypoint; taking the shortest time through the joint position spline path as a target, taking joint space constraint conditions and Cartesian space constraint conditions as constraints, obtaining a relationship between path parameters of the joint position spline path and time; and obtaining joint position trajectory planning of the robot according to the relationship between the path parameters of the joint position spline path and the time. The method can improve the operation efficiency of the robot.

The application provides a Bessel curve posture interpolation trajectory optimization method, system and computer device, a mapping relationship between a posture trajectory in a Cartesian space and a Lie algebra space tangent vector is established, a Bessel curve interpolation trajectory in the Lie algebra space is constructed, and based on a curvature radius change model and a speed change model of the Bessel curve interpolation trajectory, the smoothness and stability of a multi-section posture interpolation trajectory when a rotation axis changes are improved. Furthermore, based on a Jacobian matrix mapping of a mechanical arm joint space and the Cartesian space, a joint space speed constraint is added, and a joint space maximum angular velocity constraint problem of the mechanical arm is considered to further constrain the Cartesian space speed, bidirectional feedback of the joint space and the Cartesian space is realized, the stability of each joint motion of the mechanical arm is improved, the speed curve of each joint of the mechanical arm is continuous, and the precision of the mechanical arm trajectory tracking is improved.

The embodiment of the invention provides a redundant joint control method and device, equipment and a medium. The method comprises the following steps: acquiring tail end position data corresponding to a tail end position influenced by redundant joint movement in a joint space; determining an obstacle avoidance track of the redundant joint based on the tail end position data, and determining a speed function corresponding to the obstacle avoidance track; determining a constraint condition set corresponding to the speed function, and optimizing the speed function based on the constraint condition set to obtain an optimized speed function; and a control strategy of the redundant joints is determined based on the optimized speed function, and the redundant joints are driven to move based on the control strategy. According to the method, the redundant joints can accurately avoid obstacles in a complex environment, and safe, stable and efficient movement can be achieved.

The invention discloses a man-machine collaborative robot anisotropic admittance control method based on an offline muscle-bone performance model. Aiming at the bottleneck that the existing admittance control neglects the biomechanical heterogeneity of a human body and the inverse dynamics calculation is time-consuming, the invention constructs a control framework of offline model construction-online real-time estimation. The method comprises the following steps: establishing a human body muscle-bone model offline, performing simulation calculation on a muscle-bone force ellipsoid in a full operation space, and training a deep neural network to establish mapping from a joint space to mechanical properties; the real posture of the human body is calculated through online fusion of vision and foot motion data; and calculating the matching degree of the interaction force and the ellipsoid main shaft, and constructing a direction-dependent anisotropic admittance controller. The impedance characteristic of the robot and the human muscle-bone performance space are isomorphic, high stability in the dominant force application direction and high compliance assistance in the vulnerable direction are achieved, and the muscle-bone injury risk of an operator is effectively reduced.

Systems and methods for planning and assisting orthopaedic surgical procedures include a computer system and a robotic surgical device. The computer system receives a set of target joint space values including a target extension space value and a target flexion space value. The computer system initializes a surgical plan including planned resection heights and determines a set of current joint space values based on the surgical plan. The computer system adjusts one or more planned resection heights of the surgical plan until the set of current joint space values matches the set of target joint space values. The computer system may control the robotic surgical device according to the surgical plan.

This application belongs to the field of medical devices and protective equipment, specifically involving a design method and layered structure for an enhanced mouthguard based on musculoskeletal stability optimization. The method includes: collecting multimodal data such as the full dentition morphology, jawbone structure, mandibular movement trajectory, surface electromyography, and plantar pressure of the subject; constructing a correlation system between mandibular position and overall stability using a radial basis function neural network; setting anatomical boundaries, joint spaces, and muscle symmetry constraints; and using a genetic algorithm to iteratively optimize and lock in a personalized musculoskeletal stability position; based on this, performing layered digital design of the mouthguard's flexible base layer and posterior tooth retention components, and then 3D printing manufacturing. This application, through precise optimization of jaw position, achieves a leap from passive protection to actively enhancing body stability in sports mouthguards, significantly improving exercise efficiency and wearing comfort while ensuring physical protection.

The invention relates to the technical field of orthopedic implantation, in particular to an anatomical adaptive 3D printing porous tantalum atlantoaxial lateral mass fusion cage which comprises a fusion cage body, and the structure of the fusion cage body is limited to be capable of being placed in a joint gap between an atlantoaxial lateral mass and an axis lateral mass; an upper contact surface and a lower contact surface are formed on two opposite sides of the fusion cage main body, the upper contact surface is used for being in contact with a lower joint surface of an atlas lateral mass, and the lower contact surface is used for being in contact with an upper joint surface of an axis lateral mass; according to the fusion cage, the fitness of the fusion cage body and the joint surfaces of the atlas lateral mass and the axis lateral mass is improved, load dispersion is facilitated, and the interface micro-motion risk is reduced; the porous net rack provides a communication space for bone tissue ingrowth, improves bone-implant combination conditions, and is beneficial to fusion stabilization; the clamping hole is matched with the limiting structure to improve the grasping, pushing and positioning stability of the instrument, and relative rotation or axial movement in the operation is reduced; the integrity and reliability of the structure are improved through the circumferential continuous closed side wall and overall additive manufacturing forming, and the loosening risk is reduced to a certain degree.

The application provides application of SEMA3E protein in preparation of a drug for treating rheumatoid arthritis and promoting cartilage regeneration, and belongs to the technical field of biological medicine. The amino acid sequence of the SEMA3E protein is shown as SEQ ID No. 1. Research results show that one month after injection of the SEMA3E protein solution, the joint swelling degree of the double hind limbs of an animal model is reduced, the joint space and integrity are restored to normal, the cartilage thickness is increased, and the phenomenon of synovial cell infiltration and invasion into the cartilage is eliminated. That is, the SEMA3E protein can well reduce joint cavity inflammation and improve damaged joints.

An orthopedic cutting instrument can be used to cut and release soft tissue to mobilize a bone for subsequent realignment of the bone. In some examples, the cutting instrument is configured with a handle and a cutting head. The cutting head has multiple cutting surfaces, such as a lead cutting surface and side cutting surfaces extending angularly away from the lead cutting surface. A mirror set of cutting surfaces may be provided on the opposite side of the cutting head. The cutting surfaces may be arranged to allow controlling cutting of soft tissue while limiting inadvertent deep penetration of the cutting instrument. In addition, the cutting surfaces may be arranged to allow back-and-forth cutting movement of the cutting head, which can be useful when working in a tight joint space.

The application relates to a robot force control method, device, robot and storage medium, the robot force control method comprises the following steps: acquiring the contact force and torque of a tool carried by a robot and an environment in a tool coordinate system; controlling the contact force and torque in the tool coordinate system by using a mobility control and an integral control to obtain a position compensation amount in the tool coordinate system; converting the position compensation amount in the tool coordinate system into a position compensation amount in a joint space to obtain a joint compensation amount, and synchronously controlling the position and force of the tool carried by the robot according to the joint compensation amount. The robot force control method provided by the application improves the responsiveness, stability and steady-state accuracy of robot force control.

The embodiment of the specification provides a mechanical arm action control method and system, and relates to the technical field of robots. The method comprises the following steps: acquiring a key frame sequence comprising K key frame images; performing human pose estimation and joint angle calculation on the key frames to obtain a calculation result comprising N human joint angles; performing human-robot joint space nonlinear mapping based on the calculation result of each of the K key frames in the key frame sequence to obtain a preliminary joint angle sequence corresponding to each of N robot joints; optimizing the N preliminary joint angle sequences to obtain N final joint angle sequences; performing YAML format conversion based on the N final joint angle sequences, and downloading the obtained joint angle trajectory data to any device controller to instruct the device controller to control the action of the connected robot arm based on the joint angle trajectory data. In this way, the action arrangement efficiency of the robot arm can be improved, and the action fluency and action reproduction accuracy of the robot arm can be improved.

The umbrella-shaped dilator comprises a connecting column and a distraction assembly, a push rod is slidably connected into the connecting column, a plurality of toothed plates are fixedly connected to the position, close to one end, of the outer end of the push rod, a connecting plate is rotatably connected to one end of the push rod, a limiting assembly is arranged at the outer end of the connecting column, and the distraction assembly is located at the end of the connecting column. The distraction assembly comprises a plurality of distraction plates and a plurality of second gears, after a connecting column is accurately inserted into a joint gap and enters a designated position, one end of a push rod can be pressed to enable the push rod to slide relative to the connecting column, so that the second gears rotate, and a connecting shaft can be synchronously driven to rotate; therefore, a plurality of distraction plates are controlled to perform unfolding movement, the purpose of exposing is achieved, the size of joint gaps is enlarged, a better operation visual field is provided, a doctor can observe and process structures in joints more easily, and the probability of damaging surrounding tissues is reduced.

Decortiating screws and insertion tools for implanting the decorticating screws including screws that anchor into a first and a second bone to fuse the two bones together. The screws include a rotatable bladed section to decorticate a joint space between the first and second bone. The screws also optionally include a cap to secure the screws in the bone and apply compression to the joint to be fused. In some embodiments, the decorticating screws are useful for sacroiliac (SI) joint fusion.

This application provides a method, device, and system for dexterous hand teleoperation based on a data glove, applied in the field of smart grid technology. The method is applied to an electronic device, which is communicatively connected to both a data glove and a dexterous hand worn on the operator's hand. The method includes: acquiring motion data of the operator's hand collected by the data glove, the motion data including the first joint degrees of freedom corresponding to each joint of each finger; performing coupling mapping processing on the motion data based on a preset human hand prior knowledge base to obtain adjusted motion data conforming to the natural movement pattern of the human hand; using a Kalman filter algorithm to smooth and predict the state of the adjusted motion data to obtain a target motion sequence; and generating joint space control commands for the dexterous hand based on the target motion sequence to drive the dexterous hand to reproduce the operator's hand movements. This method aims to improve the level of intelligence, the naturalness, fluency, and coordination of dexterous hand movements.

The application belongs to the technical field of mechanical arm joint space trajectory planning, and aims to provide a mechanical arm joint space trajectory planning method based on model prediction path integral, so as to realize mechanical arm joint space trajectory optimization planning. The method comprises the following steps: firstly, the joint configuration of the mechanical arm is utilized, the configuration symbolic distance function (CSDF) is utilized according to the configuration of the mechanical arm and the point cloud of the scene, and the estimation value of the distance and gradient of the whole mechanical arm body to the nearby obstacle is obtained; then, a fast, online and global trajectory generator is constructed based on the model prediction path integral method, the initial and target mechanical arm configurations are received, the collision cost of the current mechanical arm configuration space is estimated according to the estimation value of the distance and gradient of the whole mechanical arm body to the nearby obstacle, and a globally optimal trajectory is generated for the mechanical arm to execute. The application is mainly applied to mechanical arm design and manufacturing occasions.

A surgical robotic system has a surgical robotic arm, and a programmed processor that determines a longest principal axis of a velocity ellipsoid for a first configuration of the arm, applies a maximum task space velocity (that is in the direction of the longest principal axis) to an inverse kinematics equation which computes a potential joint space velocity, computes a ratio of i) the potential joint space velocity and ii) a joint space velocity limit of the arm, and applies the ratio to an initial joint space velocity, to produce a regulated joint space velocity. Other aspects are also described and claimed.

Robotic surgical systems and methods involving employing machine learning models to improve surgical robotic performance in task space and / or joint space. The robotic manipulator includes a plurality of links and joints and supports a surgical tool. A control system is coupled to the robotic manipulator. For task space control, the control system computes haptic forces that are intended to constrain specified degrees of freedom of the surgical tool and implements the machine learning model to refine the computed haptic forces in attempt to achieve constraint of the surgical tool according to the specified degrees of freedom. For joint space control, the control system computes joint torques for the joints of the robotic manipulator and implement the machine learning model to refine the computed joint torques in attempt to achieve desired joint positions. The machine learning models may use data-driven control schemes.

This invention discloses a method and system for predicting the demand for total knee arthroplasty (TKR), relating to the field of clinical decision support. The method includes: acquiring knee MRI images; automatically segmenting key structures of the joint space using a deep convolutional neural network to obtain the volume of interest (VOI); extracting radiomics features according to the IBSI standard using the SERA tool; and finally constructing a joint space plus clinical features radiomics model (JSC-RM) by combining the Knee Osteoarthritis Outcome Survey (KOOS) score to predict whether TKR will be performed within the next 1-4 years. The method employs LASSO feature selection and shallow neural network modeling, combined with Youden's index to set thresholds, resulting in predictive performance superior to existing models. It significantly improves the consistency and accuracy of resident physicians' judgments on the timing of TKR, achieving intelligent preoperative risk intervention.