674 results about "Humanoid robot" patented technology

The invention provides a wheel driving robot finger device, belonging to a robot technical field which comprises a base, a motor, a reducer, a first gear, a second gear, a close joint shaft, a middle part finger, a far joint shaft and a terminal finger section as well as a driver, a transmission part, a driven wheel, a spring part. The middle part finger is sleeved on the close joint shaft. Two terminals of the spring part are respectively connected with the middle and the terminal finger sections. The device uses a pair of wheel mechanisms to sleeve a plurality of active middle part fingers with the decoupling effect of the spring part comprehensively to realize the special effect that the double joints drive the finger to bend so as to catch the objects. With simple structure, reliability, low cost, convenient installation and maintenance, small volume and light weight, the wheel driving robot finger device similar to human fingers is especially suitable for being used as a thumb of the hand of the humanoid robot or a part of other fingers that uses fewer drivers to drive more rotation joints to automatically adjust to catch the objects of different shapes and sizes.

The invention provides a humanoid robot control method based on artificial intelligence, a system and the humanoid robot. The method comprises the following steps of receiving a voice signal input by a user and/or an image signal; according to the voice signal and/or the image signal, determining a user intention; processing the user intention and feeding back a processing result as a multi-modal output mode to the user, wherein the multi-modal output mode comprises one or more of a motion output mode of the humanoid robot, an image or video output mode and an audio output mode. By using the method, according to the collected voice signal and/or image signal of the user, after artificial intelligence analysis, the humanoid robot is autonomously controlled to interact with the user as several modes so that an artificial intelligence result can be visually and effectively displayed and an affine and effective effect is achieved in propaganda, demonstration and service fields.

Disclosed is a humanoid robot apparatus, method and computer-readable medium thereof related to lifting and holding a heavy object having a weight unknown to the robot, by measuring an external force acting on the robot. Linear momentum and rotational momentum are compensated for stepwise according to the degree of stability of the robot which is determined based on the measured external force. Accordingly, the robot stably lifts and holds the object without losing its balance.

A human-type link system, such as a humanoid robot having a dynamically feasible motion of the link system that is generated when a reference joint acceleration that is only calculated from a kinematical constraint condition is determined not feasible by an evaluation of external force computed based on an inverse dynamics calculation, or is generated by calculating from a dynamic constraint condition and a kinematical constraint condition simultaneously, the dynamic constraint condition is formulated by using an actuation space inverse inertial matrix that represents the relation of force acting on the link system and the acceleration of the link system caused by the force.

Generally the background of the present invention is the field of artificial vision systems, i.e. systems having a visual sensing means (e.g. a video camera) and a following processing stage implemented using a computing unit. The processing stage outputs a representation of the visually analysed scene, which output can then be fed to control different actors, such as e.g. parts of a vehicle (automobile, plane, . . . ) or a robot, preferably an autonomous robot such as e.g. a humanoid robot.

The invention discloses a variable-rigidity flexible joint of a humanoid robot, which mainly comprises a variable flexible joint driver and a 2D differential drive joint mechanism, wherein, the variable flexible joint driver mainly comprises a micro-drive unit, a motor support and an elastic unit; and the 2D differential drive joint mainly comprises flexible cable input wheels, an output wheel and a flexible cable. The variable-rigidity flexible joint is characterized in that the variable-rigidity flexible joint driver introduces a special elastic element which can realize variable rigidity to adapt to the need of the joint rigidity in different walking stages and store/release energy and absorb shock; the variable flexible joint driver is connected with the 2-DOF differential drive joint mechanism through the flexible cable and has no redundant drive; and the variable-rigidity flexible joint adopts the 2-DOF differential mechanism and flexible cable transmission, thus having simple structure, small friction, no hysteresis error and reduced joint size of the robot compared with a gear design, and realizing drive torque redistribution according to the angle of energy consumption distribution of human.

The invention discloses a six-degree-of-freedom humanoid robot arm, and relates to a robot arm. The invention aims to solve the problems that the existing robot arm is cumbersome in joint structure, heavy in self weight, low in load bearing ratio and complicated to control. A shoulder rotating joint, a shoulder joint, an upper arm, an elbow rotating joint, a elbow swing joint, a fore arm, a wrist rotating joint, a wrist swing and a hand are sequentially arranged from top to bottom, wherein an arm swing motor is connected with a worm by virtue of a conveyor belt, an arm rotating motor is connected with a shoulder swing support by virtue of a conveyor belt, an upper arm shell is arranged between a shoulder joint and an elbow joint, an elbow rotating drive motor and a speed reducer are sequentially arranged in the upper arm shell from top to bottom, an elbow swing joint motor is arranged in an elbow joint shell and is connected with an elbow joint conveyor belt, an elbow joint speed reducer is arranged in the elbow joint shell, a hand connecting support is arranged between the fore arm and the hand, a wrist joint swing motor is arranged on one side of the hand connecting support, and a wrist joint rotating motor is arranged at the upper end of the hand connecting support. The six-degree-of-freedom humanoid robot arm is applied to a humanoid robot.

A system and method is disclosed for predicting a fall of a robot having at least two legs. A learned representation, such as a decision list, generated by a supervised learning algorithm is received. This learned representation may have been generated based on trajectories of a simulated robot when various forces are applied to the simulated robot. The learned representation takes as inputs a plurality of features of the robot and outputs a classification indicating whether the current state of the robot is balanced or falling. A plurality of features of the current state of the robot, such as the height of the center of mass of the robot, are determined based on current values of a joint angle or joint velocity of the robot. The current state of the robot is classified as being either balanced or falling by evaluating the learned representation with the plurality of features of the current state of the robot.

The invention provides a motion trajectory planning method of mechanical arms of a humanoid robot for preventing collision. In the prior art, the collision problem is not solved fundamentally. The method adopts a joint space-based interpolation method to solve the collision problem between the mechanical arms and a table caused by motion trajectory generation of the mechanical arms, and mainly aims at operation of humanoid arms of the humanoid robot oriented to tabletops or objects similar to tabletops. The mechanical arm freedom degree includes three freedom degrees of the shoulder, two freedom degrees of the elbow and two freedom degrees of the wrist. The concrete implementation method comprises under the premise of ensuring completion of target operation at a fixed moment, properly bending the elbow at the collision occurring moment during the motion of the mechanical arms to prevent collision. With such scheme, the mechanical arms can move without collision while realizing high flexibility and large operation space.

A robot using less storage and computational resources to embody panoramic attention. The robot includes a panoramic attention module with multiple levels that are hierarchically structured to process different levels of information. The top-level of the panoramic attention module receives information about entities detected from the environment of the robot and maps the entities to a panoramic map maintained by the robot. By mapping and storing high-level entity information instead of low-level sensory information in the panoramic map, the amount of storage and computation resources for panoramic attention can be reduced significantly. Further, the mapping and storing of high-level entity information in the panoramic map also facilitates consistent and logical processing of different conceptual levels of information.

The invention relates to the field of robot control, in particular to a method, device and system for self-adaption balance control of a humanoid robot in a complex terrain. The method comprises the following steps of establishing a connecting rod model of a robot; calculating a corresponding foothold; adjusting the joint angle value of the robot; monitoring the mass center curve of the robot, receiving gyroscope sensor data, and judging whether the robot is in a balanced state; receiving a joint angle feedback value and the gyroscope sensor data when the robot is in an unbalanced state, and optimizing and adjusting the foot movement curve of the robot; enabling the robot to be self-adaptively subjected to balance control in the movement process; optimizing the joint angle value and relevant parameters of the robot. The robot can be applied to movement balance control of biped and quadruped robots and the like, the application range is wide, the self-adaptive capacity of the robot to an application environment can be greatly enhanced, and the hardware loss can be effectively reduced in the actual application process.

The invention discloses a mechanism of a humanoid robot hand, which is composed of a palm, five fingers and a mechanical interface. The five fingers are installed on the palm, and the root of the palm is provided with a mechanical interface. The connection between the mechanism and the robot arm. In the humanoid robotic hand mechanism of the present invention, the thumb and forefinger each have a degree of freedom and are respectively driven by a motor; the middle finger, ring finger and little finger share a degree of freedom and are driven by the same motor, and the transmission of the three fingers adopts the same modular design, The only difference lies in the length of the distal knuckles of the three fingers. The first two joints of the index, middle, ring, and little fingers are kinematically coupled individually. There is a motion decoupling device at the connection shaft between the proximal knuckles of each finger and the palm. When the proximal knuckles of the fingers are blocked from touching the object, the other knuckles can continue to move to complete the envelope grasping of the object.

The invention provides a muscle strength model optimizing method for humanoid robot synergic movement. Programming and modeling are carried out on a human skeletal muscle simulation model, and a humanoid robot is designed and developed by reference to an experiment object; the humanoid robot is controlled to do the same movement by reference to the experiment object; movement detection data of the humanoid robot and output data of the human skeletal muscle simulation model are compared, design parameters of the humanoid robot and a muscle strength prediction formula in the simulation model are modified repeatedly until the design parameters and the formula are similar, and an optimized muscular strength prediction model is obtained. The muscle strength model optimizing method for the humanoid robot synergic movement can solve the problems that muscular strength during body movement can not be directly measured through experiments in biomechanics researches of a skeletal system and a muscular system, can only be calculated by means of a muscular strength model and is uncertain, and accuracy of the simulation model is improved.

The invention relates to a robot walking control method based on the determined study theory. The method comprises the processes such as the establishment of robot walking model, the establishment of referenced gait model, the study on the neural network, the establishment of constant neural network, the completion of walking task by utilizing the constant RBF neural network, etc. The invention overcomes the disadvantages of learning ability in the current neural network study and the control method and realizes the accurate study of the unknown dynamic model of a robot closed-loop control system along the periodic gait track of the robot within a local area, and can study the effective knowledge of the system dynamics during the stable dynamic control process and apply the knowledge to the subsequent same or similar tasks successfully. The method not only can realize the rapid walking on the basis of energy saving, but also provides the powerful support for the development of the humanoid robots.

The invention provides a control method for eliminating the upper body posture shaking of a double-foot humanoid robot. The robot is provided with a waist part and a posture sensor. The method comprises the following steps of: generating a planned gait of the robot; measuring the inclination angle and the angular speed of the upper body of the robot through the posture sensor; calculating the correction of a joint of the waist part according to the inclination angle and the angular speed; and adjusting the joint according to the correction so as to eliminate the upper body posture shaking of the robot. In the method, only the waist joint is adjusted without affecting the landing time of the robot; and the method achieves effects in the entire walking process or operating process of the robot.

The invention relates to a remote control humanoid robot system based on an exoskeleton human posture information acquisition technology, and belongs to the technical field of robots. A humanoid robot lacks freedom of the lower body, and cannot simulate the action of the human lower limb. Exoskeleton type human posture information acquisition clothes lack a posture acquisition device of ten fingers. The exoskeleton type human posture information acquisition clothes of the system are worn on a user, and human action information is acquired through a sensor action acquisition module. The human action information is transmitted to a robot control module through a wireless communication module to control the humanoid robot to perform corresponding action operation. The system is suitable for the users of different figures to use, and the humanoid robot can reproduce human upper body actions of 16 degrees of freedom in real time.

The invention discloses a food shock absorbing mechanism for an anthropomorphic robot, which comprises soles, wherein damping columns are arranged on the soles; upper surfaces of the damping columns are provided with upper pressure plates; force transducers and upper cover plates are arranged on the upper pressure plates; the upper cover plates are connected with the soles through four upper cover plate mounting holes; four groups of adjusting washers are arranged between the upper cover plates and the soles; the force transducers are connected with legs of the robot; the number of the damping columns is four, and the four damping columns are connected with the soles through the four damping column mounting holes which are positioned on the soles; front ends of the soles are provided with front sole bevels, and rear ends of the soles are provided with rear sole bevels; and non-skid mats are arranged below the soles. The invention designs the more compact and more effective shock absorbing mechanism, realizes continuous flexible adjustment of the shock absorbing mechanism, and can make the anthropomorphic robot easier to meet different operation requirements.

The invention discloses a multi-degree-of-freedom foot plate for a humanoid robot, and belongs to the technical field of robots. The multi-degree-of-freedom foot plate comprises a foot plate mechanism and a driving mechanism, wherein the foot plate mechanism consists of a central fixing plate and four foot plates; the front side and the rear side of the central fixing plate are hinged with two connecting plates respectively; each connecting plate is connected with a foot plate through a hinge; a rotating shaft of each hinge is provide with a torsion spring; an ankle joint connecting frame of the humanoid robot is fixedly arranged on the central fixing plate and is used for connecting ankle joints of the humanoid robot; and the driving mechanism is mainly stretched and retracted through a driving motor in combination with a spring so as to drive all the connecting plates in the foot plate mechanism to do pitching motion. The foot plate has the advantages that: the problem of incapability of matching the foot plate mechanism with an uneven ground surface is solved, and the foot plate mechanism has a passive structure, so that control complexity and structural complexity are effectively reduced without driving; and the driving mechanism is a flexible variable stiffness driving mechanism, so that impact absorption capacity is improved, and the robot can walk efficiently and stably.

The invention relates to a robot foot mechanism with flexible joints. The existing robot has poor foot impact adsorbing effect. The robot foot mechanism comprises toe plates, heel plates, sole plates, flexible hinges, spring plates, heel vibration attenuation devices, a six-dimensional force moment sensing device and an ankle support seat, wherein the toe plates and the sole plates are connected by the flexible hinges; the sole plates are connected with the heel plates by the spring plates; the bottom surfaces of the toe plates, the sole plates and the heel plates are provided with rubber layers; the flexible hinges, the spring plates and the vibration attenuation devices are all symmetrically arranged along the proceeding direction; each flexible hinge is formed by connecting two flexibly deformed rectangular rings and is formed by cutting and processing the whole line; each rectangular ring is provided with a groove vertical to the proceeding direction for adsorbing deformation; and the thickness of the middle of the spring plates is less than the thickness of two ends. In the robot foot mechanism, a humanoid robot can walk more stably by increasing the degree of freedom of passive toes, and the tread of the humanoid robot is more stable and natural.