Abstract: A method for obtaining a feature extraction model, a method for human fall detection and a terminal device are provided. The method for human fall detection includes: inputting a human body image into a feature extraction model for feature extraction to obtain a target image feature; in response to a distance between the target image feature and a pre-stored mean value of standing category image features being greater than or equal to a preset distance threshold, determining that the human body image is a human falling image; and in response to the distance being less than the preset distance threshold, determining that the human body image is a human standing image. The feature extraction model is obtained based on constraint training to aggregate standing category image features and separate falling category image features from the standing category image features.

Abstract: An obstacle avoidance control method for a robot includes: obtaining, by a depth camera perception system, envelope motion information of each movable obstacle in a target operating environment in a current control cycle, and accessing a pre-stored actual voxel block position of each environmental obstacle in the target operating environment, wherein the actual voxel block position of each environmental obstacle was measured by the depth camera perception system before the movable obstacles were present in the target operating environment; and determining a number of target obstacles that need to be avoided by a number of key obstacle-avoidance parts of a target robot in the target operating environment according to all of the envelope motion information and all of the actual voxel block positions.

Abstract: A target identification method includes: obtaining an image containing a target to be identified; performing feature extraction on the image to obtain image features in the image; and inputting the image features into a target identification network model to obtain an identification result that determines a class to which the target to be identified belongs. The target recognition network model includes a loss function that is to constrain a first distance corresponding to each triplet in a number of triplets and a second distance corresponding to each triplet in the triplets. The first distance represents a distance between anchor image features and positive sample image features in each triplet in the triplets, and the second distance represents a distance between the anchor image features and a class center mean of a number of classes in each triplet in the triplets.

Abstract: A robot control method, and a computer-readable storage medium and a wheel-legged biped robot using the same are provided. The method includes: determining a kinetic model of the wheel-legged biped robot; determining, using the kinetic model, a sliding surface of the wheel-legged biped robot; determining, according to the sliding surface, a double power reaching law and a sliding mode control law of the wheel-legged biped robot; and controlling, according to the sliding surface, the double power reaching law and the sliding mode control law, the wheel-legged biped robot. Through the above-mentioned method, the adaptability of the wheel-legged biped robot to uncertain external disturbances can be enhanced, thereby improving its robustness to effectively maintain its balance even in the environment with complex terrain.

Abstract: A method includes: obtaining heat maps including a predetermined number of key points of a human body; performing depth separable convolution on a feature map corresponding to one of the heat maps corresponding to each of the key points and a convolution kernel of a corresponding channel of the human body posture recognition model to determine a key point feature map corresponding to each channel of the human body posture recognition model; performing local feature fusion processing and/or global feature fusion processing on the key point feature map corresponding to each channel to obtain fusion posture feature maps; determining a linear relationship between the channels of the human body posture recognition model based on the fusion posture feature maps; and updating weight coefficients of the corresponding channels of the human body posture recognition model by using the linear relationship between the channels of the human body posture recognition model.

Abstract: A method for avoiding singularities of a robotic arm includes: calculating a virtual environment external force required by the robotic arm to avoid singularities based on current joint positions of joints on the robotic arm when it is determined that the robotic arm needs to avoid singularities; obtaining a current end force of the robotic arm and a desired end trajectory of the robotic arm; performing admittance control calculation based on the virtual environment external force, the current end force and the desired end trajectory to obtain a corrected end trajectory of the robotic arm; and controlling the robotic arm to move based on the corrected end trajectory.

Abstract: A user exercise detection method applicable in a robot includes: obtaining first measurement data from at least one inertial measurement unit (IMU) sensor that is arranged at a designated body part of the user, and detecting a posture of the user relative to the robot based on the first measurement data; obtaining second measurement data from the at least one IMU sensor, and determining whether an exercise of the user corresponding to the posture is detected according to a preset threshold parameter and the second measurement data; in response to detection of the exercise, obtaining exercise data when the user performs the exercise multiple times through the at least one IMU sensor; and adjusting the threshold parameter according to the exercise data.

Abstract: A method for determining a pose of a robot having a lidar including: obtaining a first pose of the robot in a map coordinate system; determining first positions of laser points corresponding to the lidar in the map coordinate system according to the first pose when the lidar performs laser scanning; determining matching scores between the first positions and grids where the first positions are located according to the first positions and mean values of the grids where the first positions are located, wherein the grids are grids in a probability map corresponding to the map coordinate system; determining a first confidence level for the first pose based on the matching scores; and determining a target pose according to the first confidence level.

Abstract: A method for controlling a robotic arm that includes an end effector and a sensor that are mounted at an end of the robotic arm includes: obtaining, by the sensor, n gravity matrix data, wherein the n gravity matrix data are gravity matrix data of the end effector in an end coordinate system when the robotic arm is in a different poses, n?3; determining n rotation transformation matrices from a base coordinate system of the robotic arm to the end coordinate system when the robotic arm is in n different poses; calculating coordinates of a center of mass and mass of the end effector based on the n gravity matrix data and the a rotation transformation matrices; and controlling the robotic arm based on the coordinates of the center of mass and the mass.

Abstract: A robot control method includes: building a two-wheeled inverted pendulum model based on a wheel-legged robot; constructing initial state-space equations based on the two-wheeled inverted pendulum model; linearizing the initial state-space equations to obtain the state-space equations for a linear time-invariant system; obtaining a quadratic performance objective function according to the state-space equations for the linear time-invariant system; and solving the quadratic performance objective function by a linear quadratic regulator to obtain wheel torques of the wheel-legged robot, and controlling the wheel-legged robot according to the wheel torques.

Abstract: A swimming pool cleaning system includes: a pool cleaning robot (10) that is to at least clean a floor and pool walls of a swimming pool; and a surface cleaning device (20) that is to at least clean a pool surface of the swimming pool. The surface cleaning device (20) is wirelessly connectable to an external control device and has a connecting cable (21) that electrically connects the surface cleaning device (20) to the pool cleaning robot (10), so that the pool cleaning robot (10) communicates with the external control device via the surface cleaning device (20).

Abstract: A mapping method, a computer-readable storage medium, and a robot are provided. The method is applied to a robot including a first lidar and a second lidar, where the first lidar is installed at a position higher than that of the second lidar. The method includes: obtaining a first laser key frame; calculating a current pose of a robot based on the first laser key frame; updating a first probability map based on the current pose and the first laser key frame; obtaining a second laser key frame; updating a second probability map based on the current pose and the second laser key frame; and generating a fused grid map for navigating the robot based on the updated first probability map and the updated second probability map, thereby greatly improving the stability of positioning and navigation.

Abstract: A robotic arm angle interval inverse solving method and a robotic arm using the same are provided. The method includes: obtaining a joint angle calculation model and a differential relationship model of a target joint of the robotic arm; obtaining extreme arm angles corresponding to a joint angle of the differential relationship model at extreme values based on the differential relationship model; obtaining a joint arm angle interval corresponding to the target joint based on the extreme arm angle and the joint angle calculation model; and obtaining a target arm angle interval corresponding to the robotic arm based on the joint arm angle interval corresponding to the target joint of the robotic arm. In comparison with the existing method to solve the arm angle interval of the robotic arm, a more accurate arm angle interval can be obtained.

Abstract: A robot calibration method, a robot, and a computer-readable storage medium are provided. The method includes: obtaining operation space information of the execution end of the robot; obtaining operation space points after gridding an operation space of the robot by gridding the operation space based on the operation space information; obtaining calibration data by controlling the execution end to move to the operation space points meeting a preset requirement; and calibrating the hand and the image detection device of the robot based on the obtained calibration data. In this manner, the operation space points are determined by gridding the operation space based on the operation space information, and the execution end can be automatically controlled to move to the operation space points that meet the preset requirements so as to obtain the calibration data in an automatic and accurate manner, thereby simplifying the calibration process and improving the efficiency.

Abstract: A robot joint configuration determining method, a robot using the same, and a computer readable storage medium are provided. The method includes: simulating a joint model of a first joint of the robot using first motion deviation data to obtain first result data; simulating the joint model using second motion deviation data to obtain second result data; taking the motion deviation data corresponding to one of the first result data and the second result data meeting one or more preset conditions as a target motion deviation data for the first joint; and determining type information of a reducer in a configuration information of the first joint based on the target motion deviation data. In the present disclosure, the motion deviation of the first joint that is relatively accurate can be obtained through the results of the two simulations.

Abstract: A person re-identification method, a storage medium, and a terminal device are provided. In the method, a loss function used during model training is a preset distribution-based triplet loss function constraining a difference between a mean of a negative sample feature distance and a mean of a positive sample feature distance to be larger than a preset difference threshold; where the positive sample feature distance is a distance between a feature of a reference image, and a feature of a positive sample image, and the negative sample feature distance is a distance between the feature of the reference image and a feature of a negative sample image. In this manner, it can constrain the mean of the positive sample feature distance and that of the negative sample feature distance, thereby improving the accuracy of person re-identification results.

Abstract: A method for detecting contact of a swinging leg of a robot with ground includes: obtaining a torque on each joint of the swinging leg when the robot is in a swing phase; estimating a force on a foot of the swinging leg by using a force Jacobian matrix based on the torque on each joint of the swinging leg, and calculating a rate of change of force of the foot in a vertical direction according to the force on the foot; and determining that the swinging leg has contacted the ground in response to a preset consecutive number of values of the rate of change of force being greater than a preset threshold.

Abstract: A multi-legged robot load balancing method, a multi-legged robot, and a storage medium are provided. The method includes: calculating a current position and velocity of a load positioned on a torso according to a value measured by a force sensor; calculating, through a feedback control law, a desired posture of the torso required for keeping a balance of the load according to the current position and the current velocity of the load; determining an expected position of virtual joints according to the desired posture of the torso, and calculating, using a full dynamics control algorithm of the robot, a joint torque for each real joint of the robot according to the expected position; and transmitting the calculated joint torques to the corresponding real joints so that the torso is moved to reach the desired posture by moving the corresponding real joints.

Abstract: A humanoid robot balance control method, a humanoid robot, and a storage medium are provided. The method includes: obtaining a task equation of each of a plurality of deconstructed tasks in a corresponding control cycle by solving a plurality of deconstructed task models using a relevant actual state and a corresponding expected state of the humanoid robot; calculating an optimal solution of a multi-task error optimization function based on each task equation; and generating a joint control instruction of the corresponding control cycle based on the optimal solution in response to the optimal solution being obtained within the corresponding control cycle so as to control corresponding joint(s) to execute the tasks. In such manner, it can ensure that the robot satisfies the necessary constraints while executing multiple tasks, and also comprehensively considers the errors of all the tasks to ensure the execution of all the tasks.