240 results about "Humanoid robot" patented technology

The invention relates to a long-range task-oriented VLA model method for a humanoid robot, which comprises the following steps of: S01, analyzing a natural language instruction through a space-time semantic analyzer to generate an atomic operation sequence with a space-time dependency relationship; s02, maintaining a task state machine by using a dynamic memory network, and tracking the task execution progress in real time; s03, integrating vision, language and sensor data through a multi-modal perception fusion engine; s04, calling a predefined action primitive based on an adaptive execution system and optimizing a motion track; and S05, performing online updating and optimization on the model through a continuous learning mechanism. According to the method, a natural language instruction is analyzed into a structured task sequence with space-time dependence through a space-time semantic analyzer, an execution sequence and preconditions are defined, the semantic understanding ability and the structuring degree of task planning are improved, and task decomposition and replanning in a dynamic environment are supported; according to the method, the LSTM and the knowledge graph are combined, and the task state is maintained in real time.

A torque protection apparatus comprising: a gearbox coupled to an axle; an output ring with first and second planar disc surfaces coupled to the gearbox output; an outer body surrounding these components; an output adaptor attached to the outer body; an inner body within the outer body; a first clutch friction plate between the output adaptor and first planar disc surface; fluid in a chamber between the inner body and outer body; and a hydraulic pressure mechanism. The pressurized fluid pushes the inner body toward the output ring, pressing the output ring against the clutch friction plate. This creates friction causing the outer body to rotate with the axle until rotational torque exceeds a predetermined threshold, at which point the clutch friction plate slides against the disc surface, protecting the gearbox from excessive torque.

The invention relates to the field of humanoid robots, and provides a control method for biped robot step-by-step gait strategy fusion in order to solve the problems that a biped robot is large in training difficulty, unnatural in gait, poor in adaptability and the like. Training various different terrain categories through an imitation learning algorithm and a reinforcement learning algorithm to obtain a gait strategy model; s2, performing pairwise fusion gait strategy switching between the gait strategy models corresponding to various different terrain categories; s3, the terrain category of the current position is recognized in real time according to an information collection unit of the biped robot, a corresponding gait strategy model is obtained through a strategy execution control unit, and the biped robot is controlled to walk in the corresponding motion state; and S4, when the terrain category of the biped robot is changed, smooth transition between the two gait strategy models is achieved through gait strategy switching, and control over gait strategy fusion of the biped robot is completed.

The invention provides a humanoid robot motion test platform, which comprises a base, a belt-type motion mechanism, a height adjusting device and a control system, and is characterized in that the height adjusting device comprises a linear driving mechanism of which the bottom is hinged to the base; the first sliding mechanism is connected with the output end of the linear driving mechanism; the second sliding mechanism is in sliding fit with the first sliding mechanism and is connected with the test platform; and the brake mechanism is used for limiting relative movement of the two. During slope changing, the two sliding mechanisms slide relatively to automatically compensate the space horizontal displacement difference, and lateral stress interference is eliminated; the high-frequency large-load stepping impact of the robot can be effectively resisted, the step loss of the system is prevented, and the unification of smooth slope change and high-rigidity and high-precision testing is realized.

A humanoid robot system comprises vision sensors for capturing image data, a computing architecture with processing hardware and memory, and a bipedal spatial perception model. The model includes a feature extractor that extracts hierarchical feature maps from input images, a robot data module that detects robot parts, and a robot vector data module that calculates three-dimensional spatial position and orientation data for each detected robot part. The feature extractor uses a feature pyramid network generating multi-scale feature maps through bottom-up and top-down pathways with lateral connections. The robot vector data module predicts 2D-to-3D point correspondences and solves perspective-n-point problems to obtain final position and orientation vectors, enabling real-time robot self-awareness and closed-loop visual servoing for precise object interaction.

The invention relates to the technical field of power supply, and discloses a humanoid robot modular distributed power supply system which comprises a power supply battery pack, a power management distribution board and a plurality of power utilization modules. The power utilization module at least comprises a control computing power unit, a sensing system, an upper limb joint module, a lower limb joint module and other joint modules; the power management distribution board is electrically connected with the power supply battery pack and each power utilization module. The power management distribution board comprises an MCU control unit, a DCDC power supply unit, a soft start unit, a high-power output unit and a voltage and current detection unit. Through a modular distributed power-on strategy and in combination with soft start pre-charging, voltage and current real-time detection and a regenerative braking absorption unit, voltage and current peaks generated at the moment of power-on of the capacitive high-power load are remarkably suppressed, the risk that a power device is damaged due to overvoltage and overcurrent impact is fundamentally avoided, and the reliability of the power device is improved. And the system reliability and the service life are greatly improved.

The invention belongs to the technical field of intelligent humanoid robots, and discloses a remote operation data acquisition and data closed-loop system for an intelligent humanoid robot, which builds an instruction, action and acquisition ternary time sequence synchronization mechanism through a time sequence coordination module, realizes dynamic coordination of the three parts by using a time sensitive network technology, effectively reduces time sequence deviation, and improves the system performance. Meanwhile, a space-time alignment algorithm of the data processing module is combined, so that the consistency of the multi-modal data in time and space dimensions is guaranteed; acquired data can accurately fit human operation logic and a robot action state, the optimization efficiency of a data closed loop is improved, and the requirements of high-precision operation scenes such as complex assembly and flexible material processing are successfully met; a quantitative association system of data quality and control effects is established by means of the evaluation module, invalid data such as sensor faults and action fuzziness can be screened in real time, and occupation of redundant storage and computing resources is reduced.

A method of generating a drum play motion of a robot includes generating a plurality of rhythms of a melody, assigning each of a plurality of notes forming a rhythm of each part to one of the right hand and the left hand of the robot, scheduling swing time of each of the right hand and the left hand to which each note is assigned, and generating a trajectory of each of a plurality of joints of the robot for playing the rhythm of each part based on the swing time of each of the right hand and the left hand, and by controlling a motion of each of the plurality of joints according to the trajectory of each of the plurality of joints generated in this way, creative drum play of a humanoid robot may be done when only a melody is input.

The invention discloses a high-rigidity three-degree-of-freedom anthropomorphic joint driven by passive decoupling of a rope. The anthropomorphic joint comprises a supporting frame and two sets of rope driving assemblies arranged on the two sides of the supporting frame. The rotary rope drive assembly is arranged at the front end of the supporting frame, the parallel mechanism assembly is installed at the front end of the rotary rope drive assembly, and the motion decoupling assembly is installed at the central axis position of the whole joint. Wherein the two rope drive assemblies are frame bodies which are driven by ropes to move front and back; the rotary rope drive assembly is a rotary table driven by a rope to rotate around the axis of the supporting frame, and the joint rotary freedom degree is achieved. According to the parallel mechanism assembly, two sets of motion branch chains are combined with frame bodies on the two sides to control pitching and yawing of the movable platform. And passive decoupling between the rotary motion and the pitching and yawing motion of the movable platform is realized through the motion decoupling assembly. According to the three-degree-of-freedom anthropomorphic joint, the three-degree-of-freedom driving ropes are passively decoupled, high rigidity is still kept under the condition that a low-load rope is used, the structural design is compact, the characteristic of decreasing progressively from the near end to the far end is shown, and the three-degree-of-freedom anthropomorphic joint is mainly used for wrist joints and ankle joints of anthropomorphic robots.

The invention discloses a multi-fingered dexterous hand operation reinforcement learning method based on a human action prediction model, and belongs to the field of humanoid robot dexterous hand tool body operation. A human action prediction model is trained by using data with three-dimensional pose marks of a human hand and an object, and is used for generalizedly generating a three-dimensional track of interaction between the human hand and the object. And a universal reward function is constructed by using the trajectory and is used for training a dexterous hand reinforcement learning strategy in simulation. Then, the migration ability of the strategy from simulation to reality is improved through simulation parameter domain randomization and course learning, and the reinforcement learning strategy obtained through training is deployed on a real world robot. According to the scheme, understanding of the future attitude of the operated object is introduced, the interaction process of the human hand and the object is predicted as a whole, the unified, simple and efficient reward function is constructed based on the prediction, the method is suitable for different operation tasks and different types of dexterous hands, and the method has the advantages of being high in generalization, high in success rate, high in reward function universality and the like.

The present application belongs to the technical field of embodied intelligent robots, and discloses a kind of embodied intelligent humanoid robot remote control data acquisition and data closed loop system, and the instruction, action, acquisition ternary time sequence synchronization mechanism is built by time sequence cooperation module, the dynamic cooperation of three is realized using time sensitive network technology, effectively reduce time sequence deviation, while combining the space-time alignment algorithm of data processing module, guarantee the consistency of multi-modal data in time and space dimension;Make the collected data can accurately fit human operation logic and robot action state, improve the optimization efficiency of data closed loop, successfully adapt to the demand of complex assembly, flexible material processing and other high-precision operation scene;Rely on evaluation module to establish the quantitative correlation system of data quality and control effect, can real-time filter invalid data such as sensor failure, action fuzzy, reduce the occupation of redundant storage and computing resources.

The invention relates to the field of intelligent robots, and discloses a gait adjustment method, device and equipment of a robot and a storage medium, and the method comprises the steps: obtaining target sampling points of feet of a humanoid robot, and coordinate values and terrain elevation data corresponding to each target sampling point; calculating a foothold return value of the humanoid robot according to the coordinate value corresponding to each target sampling point and the terrain elevation data; obtaining the maximum value of terrain elevation data of each target sampling point in a preset radius, and calculating a step kicking return value of the humanoid robot according to the coordinate values and the maximum value of the terrain elevation data; and performing gait adjustment on the humanoid robot according to the foothold return value and the step kicking return value. According to the method, the coordinates of the target sampling point and the terrain elevation data are obtained, and the two return values of the foothold and the step kicking are calculated, so that the humanoid robot is guided to carry out accurate gait adjustment, and the autonomous motion adaptability and stability of the robot in complex terrains such as stairs are improved.

The application relates to the technical field of robots, and discloses a kind of two-degree-of-freedom parallel ankle joint mechanism of humanoid robot and kinematics and mechanics solving method, including seven-link transmission structure, which is composed of two groups of closed-chain transmission of parallel four-bar linkages.Motor I and II are installed on the upper end of the lower leg, and the rotation drives link IV and III to move through link I, II, V and VI, and then coupled control ankle joint pitch and lateral freedom degree.The mechanism realizes load balancing of double motors through parallel transmission, improves equivalent torque, and can combine kinematics and mechanics solving method, so that precise control can be realized only by motor feedback, sensor cost is reduced, and is suitable for high stability motion demand of biped robot.

The invention pertains to a capture device (1) comprising an infinity mirror (4) configured to create an infinity optical effect to a person (2) and a camera (3) for capturing an image of an eye (20) of the person. The invention further pertains to an ocular examination system for examining the eye and to an ocular recognition system for identifying a person based on visual inspection of the eye, the ocular examination system and the ocular recognition system comprising such a capture device. The invention further pertains to a humanoid robot comprising the examination system and / or the ocular recognition system, wherein at least one eyeball of the of the humanoid robot at least partially comprises the capture device.

The invention discloses a human-simulated robot facial expression mechanism of a multi-degree-of-freedom micro-driver, which comprises a bottom plate, a supporting disc is fixedly arranged at the top of the bottom plate, a bracket is fixedly arranged on the supporting disc, an adjusting assembly is arranged on the bracket, a supporting frame is fixedly arranged at the top of the bracket, a shell is connected to the supporting frame, and a driving device is arranged on the shell. The shell is covered with an electronic skin layer, a limiting block is fixedly arranged in the electronic skin layer, a limiting cylinder corresponding to the limiting block is fixedly arranged on the shell, the limiting block is arranged in the limiting cylinder in a penetrating mode, a frame is fixedly arranged in the supporting frame, and an air pressure mechanism is arranged in the frame. A controller is fixedly arranged on the bottom plate; according to the humanoid robot facial expression mechanism of the multi-degree-of-freedom micro-driver, the air pump can be controlled to work, auxiliary limiting of the electronic skin layer is achieved by means of the limiting block, and therefore the installation stability of the electronic skin layer is effectively improved.

The application provides a joint module and a robot, and relates to the technical field of robots.The joint module comprises a joint assembly and a wire harness assembly.The joint assembly comprises a first joint unit and a second joint unit, has a joint axis, and is hinged to the first joint unit and the second joint unit.The first joint unit and the second joint unit can rotate around the joint axis.The wire harness assembly comprises a first connecting unit, a second connecting unit and a conducting unit.The first connecting unit is arranged on the first joint unit, the second connecting unit is arranged on the second joint unit, the conducting unit is arranged in a spiral around the joint axis, one end of the conducting unit is electrically connected to the first connecting unit, the other end of the conducting unit is electrically connected to the second connecting unit, and the conducting unit is arranged in a flexible structure or an elastic structure.The joint module provided by the application can realize high-durability and low-loss power and signal transmission in a limited space, so as to adapt to the long-term high-frequency motion requirement of a humanoid robot.

1. The name of the design product: humanoid robot sitting posture support bracket. 2. The use of the design product: the design product is used for humanoid robot sitting posture support bracket. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: perspective view.

The application discloses a point cloud data processing method, system, device and medium of a humanoid robot. The method comprises the following steps: acquiring a motion state parameter of a robot and initial point cloud data collected; performing dynamic sampling processing on the robot according to the motion state parameter and the initial point cloud data, and generating a projection image; performing multi-channel feature extraction and dynamic weight fusion processing on the projection image, and obtaining an encoded feature map; performing multi-scale residual coding processing on the encoded feature map according to an information theory constraint, and obtaining encoded data; and performing reconstruction processing on the encoded data according to the motion state parameter, and obtaining reconstructed point cloud data. The embodiment of the application can improve the processing efficiency of point cloud data and can be widely applied to the technical field of intelligent robots.

The thin-wall retainer for the humanoid robot knuckle bearing comprises a retainer body, the retainer body is provided with a hole beam, a pocket and a pocket with one side open, the hole beam is provided with an arc-shaped R-angle lockrand, and the retainer body is integrally connected with an inner flange in a cambered surface transition mode. The double improved design of local overlock optimization and overall strength strengthening is formed. The three-section overlock structure overcomes the local defects of stress concentration, abrasion, ball scratching and the like at the joint of a lock point and a pocket. The inner flange structure makes up the defects that an existing retainer is insufficient in overall rigidity, prone to torsional deformation and uneven in load transmission, the inner flange structure and the inner flange structure act synergistically, stress distribution, structural strength, failure resistance, assembly convenience, transmission precision and the like of the retainer are remarkably improved, and the problems that in the prior art, bearing capacity is insufficient, and transmission precision is poor are solved. And abrasion is caused by excessive friction, so that the service life of the thin-wall bearing is seriously influenced.

This invention relates to a humanoid robot, specifically a three-degree-of-freedom series-parallel hybrid redundant drive humanoid robot waist joint. The aim is to provide a three-degree-of-freedom redundant drive joint capable of actively adapting to complex dynamic loads, possessing high rigidity, and accommodating a large workspace. The technical solution is a three-degree-of-freedom series-parallel hybrid redundant drive humanoid robot waist joint, characterized in that: the humanoid robot waist joint includes a moving platform connected to the robot's upper torso at its top, a fixed platform connected to the moving platform at its top via a Hooke's joint and connected to the robot's lower limbs at its bottom via a drive motor, and three drive branches evenly distributed around the humanoid robot waist joint and connected in parallel to the moving platform and the fixed platform.

This invention relates to a humanoid robot, specifically a parallel rotating mechanical joint based on a ring-shaped guide rail, mimicking the rotation of a human neck. The aim is to provide a parallel rotating mechanical joint based on a ring-shaped guide rail to achieve three degrees of freedom in the movement of a biomimetic human neck joint while ensuring high rigidity and motion accuracy. Furthermore, the joint features a simplified structure, good support performance, and sufficient movement space for the neck joint. The technical solution is a parallel rotating mechanical joint based on a ring-shaped guide rail, characterized by: a head motion platform, a neck ring-shaped guide rail base, and three PSS (Personal Stability Support) link branches connected in parallel between the head motion platform and the neck ring-shaped guide rail base; the center of the head motion platform and the center of the neck ring-shaped guide rail base are connected by a composite rotating shaft.

The invention belongs to the technical field of robots, and particularly relates to a crawler humanoid machine for picking fruits and vegetables in a greenhouse, the crawler humanoid machine comprises a mobile chassis, a trunk assembly is assembled at the upper end of the mobile chassis, a head assembly is assembled at the upper end of the trunk assembly, and multi-joint arm assemblies are assembled on both sides of the trunk assembly. The picking base assemblies are assembled at the lower ends of the multi-joint arm assemblies respectively; and the multiple picking claw assemblies are assembled at the lower ends of the multiple picking base assemblies correspondingly. Pressure monitoring assemblies capable of being attached along with the shape are arranged in the first joint, the second joint and the third joint correspondingly, pressure monitoring is achieved, the device can complete multi-point-position flexible wrapping according to the shapes of the surfaces of fruits and vegetables, and the movement amplitude of each clamping point position can also be adjusted as needed; therefore, local extrusion damage to fruits and vegetables in irregular shapes is avoided, and low-damage clamping picking of the fruits and vegetables is achieved.

The application belongs to the technical field of humanoid robots, and discloses a modular mechanical thumb finger with the motion characteristics of a human thumb, which comprises a base module, a metacarpal module, a proximal phalanx and a distal phalanx. The base module provides a connecting interface with a palm or an arm robot. The metacarpal module has three active degrees of freedom and is driven by a screw block mechanism to accurately realize opposition, abduction and dumping motions. The proximal phalanx realizes bending motion. The distal phalanx is coupled with the proximal phalanx through a four-bar linkage mechanism and is decoupled through a rocker block mechanism, and has passive adaptive capability. The application highly imitates the motion function of a human thumb, has compact structure, efficient driving, and can stably complete fine opposition and gripping operations. Meanwhile, the modular design facilitates integration, and improves the operability, adaptability and intelligent level of the humanoid dexterous hand.

The application provides a humanoid robot facial expression mapping and calibration method, the facial expression mapping method constructs a self-supervised discrete expression data set, trains a multilayer perceptron model based on the data set, realizes preliminary mapping from expression parameters to rudder control signals, extracts expression parameters in a real person expression data set, generates robot rudder control signals through the model, constructs a self-supervised time sequence expression data set based on a redirection method, trains a long short-term memory network model, and realizes time sequence mapping of continuous expressions. The facial expression calibration method uses a visual capture device to obtain robot facial expression parameters in real time, gradually optimizes the rudder control signal, and makes the expression parameter response approach the target value. Through data-driven modeling and visual feedback optimization, the application realizes high-fidelity mapping from semantic expression parameters to multi-rudder collaborative control and systematic calibration, effectively improving the naturalness, accuracy and long-term stability of the robot facial expression.

This application discloses a method for fabricating the outer layer of a humanoid robot substrate using sheet winding, and the outer layer itself. The method includes: selecting a semi-cured or cured sheet as the 3D printing material, loading it into a 3D printing head system, and using a sheet nozzle to wind it layer by layer onto the outer side of the substrate along a predetermined path. Simultaneously, a three-dimensional moving platform controls the winding trajectory, allowing for adjustable winding directions between layers or in different regions. After winding, the material is thermosetting and cooled to form the final outer layer of the substrate. This method avoids the difficulties in rapid curing caused by incomplete cross-linking and insufficient fluidity in the central region of the silicone layer in traditional silicone 3D printing, as well as the problem of localized accumulation due to uneven distribution in complex curved structures. It also makes the 3D printed TUP or TPE layers less prone to separation between layers and easier to bond with a metal substrate. It is suitable for application on substrates with high curvature, such as human skin and muscles.

This invention provides a method for fault prediction and health management in a humanoid robot training field, relating to the field of robot health management technology. The method includes: collecting and preprocessing robot health data, controller logs, and interaction detection data between robots; conducting an initial health assessment; constructing a dynamic interactive health graph and inferring health decay trends using a time-series graph neural network; constructing and correcting a health-fault causal graph by combining historical fault data and historical health status data; adjusting alarm levels and verifying abnormal correlations; constructing and updating a multimodal health embedding model; obtaining the root causes of faults and health impact chains, and generating maintenance suggestions, health maintenance plans, and risk assessment reports. This invention captures the correlation characteristics of multi-robot groups through a dynamic interactive health graph, integrates a time-series graph neural network with a corrected health-fault causal graph, significantly improving the accuracy and timeliness of fault probability prediction, and achieving early warning of faults.

1. The name of the design product: toy (human-shaped robot 05). 2. The use of the design product: for human-shaped robot toy. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: perspective view.

The application provides a human-simulated robot remote operation control method, and the method comprises the following steps: acquiring a first expected pose of a waist of a human-simulated robot and a second expected pose of an end effector in a first reference coordinate system according to the control instruction; determining a target second expected pose corresponding to the second expected pose in a second reference coordinate according to the first expected pose and the second expected pose; determining expected poses of each joint of a mechanical arm in the second reference coordinate system by using the target second expected pose according to an inverse kinematics algorithm; and generating and sending a first control instruction according to the first expected pose, the second expected pose and the expected poses of each joint of the mechanical arm. The application can adjust the poses of each joint of the mechanical arm according to the change of the waist of the human-simulated robot, so as to ensure that the end effector can move to the position indicated by the second expected pose.

The invention discloses a foot driving structure for a humanoid robot and a pitching motion method, and belongs to the field of humanoid robots, the foot driving structure comprises a sole and a support frame fixed at the top end of the sole, and main bodies of a first motor and a second motor are fixed on two sides of the support frame in an up-down staggered manner; a first connecting line between the main body center point of the first motor and the main body center point of the second motor and a second connecting line between the output shaft center point of the first motor and the output shaft center point of the second motor intersect to form an intersection point, and the intersection point is located on the center line of the rear side of the supporting frame; the output axes of the first motor and the second motor are symmetrically arranged in a non-parallel mode, so that couple moment applied to the supporting frame is symmetrically balanced on the horizontal plane when the two motors are driven. According to the foot driving structure for the humanoid robot and the pitching motion method, through the dual-motor space geometry optimization layout, the integrated radial anti-loosening cover plate design and the directional lightweight groove structure, collaborative improvement of the mechanical property, the transmission reliability and the lightweight is achieved.