Abstract: The present disclosure provides a localization method as well as a helmet and a computer readable storage medium using the same. The method includes: extracting first feature points from a target image; obtaining inertial information of the carrier, and screening the first feature points based on the inertial information to obtain second feature points; triangulating the second feature points of the target image to generate corresponding initial three-dimensional map points, if the target image is a key frame image; performing a localization error loopback calibration on the initial three-dimensional map points according to at least a predetermined constraint condition to obtain target three-dimensional map points; and determining a positional point of the specific carrier according to the target three-dimensional map points. In this manner, the accuracy of the localization of a dynamic object such as a person when moving can be improved.

Abstract: A current protection circuit for a high voltage system includes: a power supply module to supply power to a load through a high voltage bus and a low voltage bus; a detection module connected to the high voltage bus and used to detect a value of current flowing through the high voltage bus; a signal processing module electrically connected to the detection module and used to amplify the current flowing through the high voltage bus; and a control module electrically connected to the signal processing module, the power supply module, and the load, and used to disconnect the load from the power supply module or perform current limiting for the load when the value of the amplified current exceeds a preset threshold.

Abstract: The present disclosure provides a speech synthesis method as well as an apparatus and a computer readable storage medium using the same. The method includes: obtaining a to-be-synthesized text, and extracting to-be-processed Mel spectrum features of the to-be-synthesized text through a preset speech feature extraction algorithm; inputting the to-be-processed Mel spectrum features into a preset ResUnet network model to obtain first intermediate features; performing an average pooling and a first down sampling on the to-be-processed Mel spectrum features to obtain second intermediate features; taking the second intermediate features and the first intermediate features output by the ResUnet network model as an input to perform a deconvolution and a first up sampling so as to obtain target Mel spectrum features corresponding to the to-be-processed Mel spectrum features; and converting the target Mel spectrum features into a target speech corresponding to the to-be-synthesized text.

Abstract: According to one aspect, an actuator of a robotic drawer is disclosed. The actuator may include a plurality of articulation components that form an articulated rack. The actuator may include a plurality of pins each coupled to an exterior of one of the plurality of articulation components. The actuator may include a transformer box coupled to a pinion and configured to move along an exterior of the articulated rack as the pinion moves along the surface. The transformer box may include a first guide configured to apply a first force to an arm of each of the pins as the transformer box moves in a first direction. The first force may cause the pin to rotate in a first rotational direction until the arm is fitted into a cam of the articulated rack such that adjacent articulation components are held in a fixed position, causing the articulated rack to extend.

Abstract: The present disclosure provides a method and an apparatus for face recognition and a computer readable storage medium. The method includes: inputting a to-be-recognized blurry face image into a generator of a trained generative adversarial network to obtain a to-be-recognized clear face image; inputting the to-be-recognized clear face image to the feature extraction network to obtain a facial feature of the to-be-recognized clear face image; matching the facial feature of the to-be-recognized clear face image with each user facial feature in a preset facial feature database to determine the user facial feature best matching the to-be-recognized clear face image as a target user facial feature; and determining a user associated with the target user facial feature as a recognition result. Through this solution, the accuracy of the recognition of blurry faces can be improved.

Abstract: A robotic motion control method provided by the present disclosure includes: obtaining a position and orientation of a starting point where the robot is currently located through a positioning sensor, and obtaining a position and orientation of a preset target point where the robot is moved to; determining an arc path and a straight path of the robot according to the position and orientation of the starting point, the position and orientation of the preset target point, and a preset arc radius; and moving the robot to the preset target point according to the determined arc path and straight path. Because there are only pure circular motion and pure linear motion which are simple during the movement of the robot, it is beneficial to improve the precision of the motion control of the robot and enable the robot to reach the target position in a reliable manner.

Abstract: The present disclosure provides a streaming voice conversion method as well as an apparatus and a computer readable storage medium using the same. The method includes: obtaining to-be-converted voice data; partitioning the to-be-converted voice data in an order of data obtaining time as a plurality of to-be-converted partition voices, where the to-be-converted partition voice data carries a partition mark; performing a voice conversion on each of the to-be-converted partition voices to obtain a converted partition voice, where the converted partition voice carries a partition mark; performing a partition restoration on each of the converted partition voices to obtain a restored partition voice, where the restored partition voice carries a partition mark; and outputting each of the restored partition voices according to the partition mark carried by the restored partition voice. In this manner, the response time is shortened, and the conversion speed is improved.

Abstract: The present disclosure provides a robot centroid position adjustment method as well as an apparatus and a robot using the same. The method includes: obtaining initial values; obtaining a waist velocity adjustment value; calculating a current value of the centroid position; and determining whether a current value of the centroid position is equal to the planning value of the centroid position; if the current value of the centroid position is not equal to the planning value of the centroid position, obtaining the current value of the centroid position to take as the initial value of the centroid position and returning to the step of obtaining the waist velocity adjustment value until the current value of the centroid position is equal to the planning value of the centroid position. In such a manner, the balance ability of the robot can be improved.

Abstract: The present invention provides a rotation angle detection method and device thereof. The method includes calculating an estimated value of a rotation angle of a motor shaft during rotation according to a second rotation angle; determining an actual range of the rotation angle according to the estimated value of the rotation angle and a detection error of the second angle sensor; determining optional values of the rotation angle based on a relative relationship between a first rotation angle and the estimated value; determining an actual rotation angle of the motor shaft, based on a value falling within the actual range of the rotation angle among the optional values, and determining an actual rotation angle of the output shaft according to the actual rotation angle of the motor shaft. The present invention can improve the measurement accuracy of the rotation angles of the output shaft of the rotating mechanism.

Abstract: A method for controlling an arm of a robot to imitate a human arm, includes: acquiring first pose information of key points of a human arm to be imitated; converting the first pose information into second pose information of key points of an arm of a robot; determining an angle value of each joint of the arm according to inverse kinematics of the arm based on the second pose information; and controlling the arm to move according to the angle values.

Abstract: The present disclosure discloses a robot control method as well as an apparatus, and a robot using the same. The method includes: obtaining a human pose image; obtaining pixel information of key points in the human pose image; obtaining three-dimensional positional information of key points of a human arm according to the pixel information of the preset key points; obtaining a robotic arm kinematics model of a robot; obtaining an angle of each joint in the robotic arm kinematics model according to the three-dimensional positional information of the key points of the human arm and the robotic arm kinematics model; and controlling an arm of the robot to perform a corresponding action according to the angle of each joint. The control method does not require a three-dimensional stereo camera to collect three-dimensional coordinates of a human body, which reduces the cost to a certain extent.

Abstract: A robotic hand includes a baseplate, a finger having multiple phalanges that are rotatably coupled to one another, a first of the phalanges having a first end rotatably coupled to the baseplate and a second end and a second of the phalanges rotatably coupled to the second end about an axis of rotation, an actuating mechanism mounted on the baseplate, the actuating mechanism configured to actuate rotation of the plurality of phalanges, and a tendon having opposite ends that are respectively attached to the second of the phalanges and the baseplate. The second of the phalanges has an engagement portion arranged around the axis of rotation, and the tendon is wrapped around a portion of the engagement portion to generate a force acting on the second end of the first of the phalanges, causing the first of the phalanges to rotate from a flexed state to an extended state.

Abstract: The present disclosure provides a robotic arm control method as well as an apparatus and a terminal device using the same. The method includes: obtaining a current joint angle of each of M joints of the robotic arm; obtaining a reference included angle based on the current joint angle of each of the M joints of the robotic arm; determining an expected included angle corresponding to the robotic arm within a target angle range based on the reference included angle and the preset included angle related evaluation function; and controlling the robotic arm based on the target joint angles of the M joints.

Abstract: A display stand includes a frame, an actuated rotary mechanism coupled to the frame, a counterweight coupled to the actuated rotary mechanism and movable in a vertical direction during rotation of the display about the axis of rotation, and an elevation mechanism. The actuated rotary mechanism includes a display holder that is configured to mount a display to the frame and rotate the display about an axis of rotation. The counterweight and the display are located at opposite sides of a vertical plane that passes through the axis of rotation such that a combined center of mass of the display, the display holder, and the counterweight lies on the vertical plane. The frame is coupled to the elevation mechanism, and the elevation mechanism is configured to move the frame up and down.

Abstract: The present disclosure provides a path tracking method as well as a mobile robot using the same. The method includes: obtaining a preset path and a current position of the mobile device; determining a forward-looking path point corresponding to the current position on the preset path; obtaining a path curvature corresponding to the forward-looking path point; and determining an adjustment velocity of the mobile device at the current position based on the path curvature corresponding to the forward-looking path point. In this manner, the adjustment velocity of the mobile device can be determined based on the curvature of the path, so as to adjust the velocity of the mobile device and improve the stability of path tracking of the mobile device at different path curvatures.

Abstract: The present disclosure provides an obstacle detection method as well as an apparatus and a robot using the same. The method includes: obtaining, through the sensor module, image(s); detecting an obstacle image of an obstacle from the image(s) according to characteristic(s) of the obstacle; extracting image feature(s) of the obstacle; obtaining, through the sensor module, a position of the obstacle; associating the image feature(s) of the obstacle with the position of the obstacle; calculating a motion state a the obstacle based on the position information of the obstacle at different moments; and estimating the position of the obstacle in a detection blind zone of the robot based on the motion state. In such a manner, it is capable of providing more accurate position information of the obstacle in the detection blind zone, which is beneficial to the robot to plan a safe and fast moving path.

Abstract: The present disclosure provides a robot visual image feature extraction method as well as an apparatus and a robot using the same. The method includes: collecting image data through visual sensor(s) of the robot, and collecting angular velocity data through inertial sensor(s) of the robot; calculating a relative pose between image frames in the image data based on the angular velocity data; extracting feature points of the first image frame in the image data; calculating a projection position of each feature point of the k-th image frame in the k+1-th image frame based on a relative pose between the k-th image frame and the k+1-th image frame; and searching for each feature point in the projection position in the k+1-th image frame, and performing a synchronous positioning and a mapping based on the searched feature point. In this manner, the feature points of dynamic objects are eliminated.

Abstract: A computer-implemented method for utterance generation, a smart device, and a non-transitory computer readable storage medium are provided. The method includes: obtaining a first utterance to be answered, generating at least one random semantic vector, inputting the at least one random semantic vector and the first utterance into a trained generator, and obtaining at least one first answer outputted by the trained generator, wherein the trained generator is obtained based on a preset generative adversarial network. Due to the random semantic vector, even for the same utterance, the smart device can generate different answers corresponding to the different random semantic vectors, the possibility of generating too many identical answers during the human-machine conversation is reduced, and the fun during the human-machine conversation is enhanced.

Abstract: The present disclosure discloses a voice conversion training method. The method includes: forming a first training data set including a plurality of training voice data groups; selecting two of the training voice data groups from the first training data set to input into a voice conversion neural network for training; forming a second training data set including the first training data set and a first source speaker voice data group; inputting one of the training voice data groups selected from the first training data set and the first source speaker voice data group into the network for training; forming the third training data set including the second source speaker voice data group and the personalized voice data group that are parallel corpus with respect to each other; and inputting the second source speaker voice data group and the personalized voice data group into the network for training.