Abstract: A terminal access method includes: sending, by a network device, uplink signal configuration information for an idle terminal to a terminal; receiving, by the network device from a first base station, uplink signal measurement information and load of the first base station, wherein the uplink signal measurement information is obtained by measurement by the first base station upon receiving an uplink signal carrying a terminal identifier from the terminal based on the uplink signal configuration information; and configuring, by the network device, mobility for the terminal based on the terminal identifier, the uplink signal measurement information and the load of the first base station, wherein the configuring mobility is configuring a candidate serving base station for the terminal such that the terminal initiates a service request to enter an active state at the candidate serving base station.

Abstract: A binocular brightness sensitivity measurement method based on a wearable display device includes: loading a first test image and a second test image which has a brightness different from that of the first test image respectively for two eyes of a user under test; adjusting the brightness of the first test image and/or the second test image until a predefined brightness sensitivity perception test condition is fulfilled; acquiring a brightness difference between the first test image and the second test image; and determining a binocular brightness sensitivity of the user under test based on the brightness difference.

Abstract: The present disclosure relates to a program verification method and apparatus, a platform, a user terminal, and an online service system, includes: acquiring a root evidence of a server-side program from a blockchain network, and acquiring a verification evidence of the server-side program from a server side, where the root evidence is written into the blockchain network after server-side program review succeeds, and the success of the server-side program review indicates a data processing method of the server-side program satisfies a preset data processing rule; verifying whether the root evidence and the verification evidence are matched, where the root evidence and the verification evidence being matched indicates the server-side program is a program that is operated in a TEE of a computer and is not modified after the root evidence is written into the blockchain network; and determining to connect a user-side program to the server-side program.

Abstract: The present disclosure discloses a point cloud-based map calibration method and system, a robot and a cloud platform. The method is applied to a cloud platform communicatively connected to a designated robot, and includes: obtaining environmental acquisition information from the designated robot; performing three-dimensional point cloud reconstruction on the environmental acquisition information, performing obstacle recognition on a three-dimensional point cloud reconstruction result, and obtaining an obstacle recognition result including obstacle information and confidence information corresponding to the obstacle information; and when it is determined that the confidence information satisfies a first preset index, sending map calibration information corresponding to the obstacle information to the designated robot, so that the designated robot calibrates map information according to the map calibration information.

Abstract: A method for controlling a robot includes: establishing a reference coordinate system; capturing a user's gaze direction of an indicated target; acquiring a sight line angle of the robot; acquiring a position of the robot; acquiring a linear distance between the robot and the user; calculating in real time a gaze plane in a user's gaze direction relative to the reference coordinate system based on the sight line angle of the robot, the position of the robot and the liner distance between the robot and the user; and smoothly scanning the gaze plane by the robot to search for the indicated target in the user's gaze direction.

Abstract: An image annotating method includes: acquiring an image collected at a terminal; acquiring voice information associated with the image; annotating the image according to the voice information; and storing an annotated result of the image.

Abstract: A motion planning method for robot arms includes: calculating an arm angle range of each pose of a tail end of a robot arm in the motion trajectory; calculating a start arm angle value of a start pose of the tail end of the robot arm in the motion trajectory; calculating an arm angle proportion according to the start arm angle value and the arm angle range of the start pose; identifying an abruptly changing arm angle range in the arm angle range of each pose according to a upper boundary curve and a lower boundary curve; calculating an arm angle of a pose corresponding to the abruptly changing arm angle range; calculating arm angles corresponding to the other poses according to the arm angle proportion; and calculating an angle of a joint of the robot arm.

Abstract: Some embodiments of the present disclosure provide an intelligent charging pile for a robot, includes: a charging loop, a protecting loop, and a communication control loop; the charging loop is connected with the protecting loop; the protecting loop is connected with the communication control loop; the communication control loop controls the charging loop to be turned off by means of controlling the protecting loop to be turned off; the communication control loop is connected with the charging loop; the communication control loop is further used for acquiring battery information data of the robot and sending, according to the battery information data, an adjustment instruction to the charging loop; and the charging loop is used for adjusting, according to the adjustment instruction, an own charging parameter and charging, according to the adjusted charging parameter, the robot.

Abstract: The present disclosure discloses a data generation method and apparatus, and a computer-readable storage medium, the method including: importing a robot model by using a game engine; simulating a Red-Green-Blue Depth (RGBD) camera by a scene capture component in the game engine; controlling a human hand of the imported robot model to move within a field of view of the RGBD camera by using a joint control module in the game engine; acquiring RGBD image data by using the RGBD camera; and generating an annotated data set with coordinates of 21 key points according to the RGBD image data and coordinate information of a 3D pose of the 21 key points.

Abstract: Provided are an ultrasonic diagnostic device, a method for generating an ultrasonic image, and a storage medium, includes: an ultrasonic probe, an acquisition assembly for a probe image, and a main control assembly connected with the ultrasonic probe and the acquisition assembly. The ultrasonic probe is configured to continuously scan an object to be detected located on an operating table to acquire corresponding ultrasonic images, and transmit the ultrasonic images to the main control assembly; a photographing direction of the acquisition assembly faces the operating table, and a photographing range covers the operating table; the acquisition assembly is configured to acquire, when the ultrasonic probe is operated, a probe image containing the ultrasonic probe in real time; and the main control assembly is configured to stitch according to the probe image the ultrasonic images to generate an ultrasonic stereo image of the object to be detected.

Abstract: Provided are an ultrasonic diagnostic device, an ultrasonic probe, a method for generating an image, and a storage medium. The ultrasonic diagnostic device includes: an ultrasonic probe, and a main control assembly connected with the ultrasonic probe; the ultrasonic probe includes a probe main body and a pose detection assembly; the pose detection assembly is configured to acquire pose data of the ultrasonic probe in real time; the probe main body is configured to continuously scan a detection object to acquire corresponding ultrasonic images, and transmit the ultrasonic images and the corresponding pose data to the main control assembly; and the main control assembly is configured to stitch, according to the pose data, the continuous ultrasonic images, so as to generate an ultrasonic stereo image of the detection object.

Abstract: The present disclosure relates to a robot and a housing thereof. The housing includes a forearm shell, an upper arm shell and a chest shell. At least one of the forearm shell, the upper arm shell and the chest shell is a flexible shell. The flexible shell includes an elastic main body layer. According to the above technical solution, the robot housing provided by the present disclosure may reduce and even avoid limitations of the housing to motion ranges of joints of the robot, and also ensures attractive appearance.

Abstract: A method for training an object identification neural network based on a distorted fisheye image includes: acquiring the distorted fisheye image, wherein the distorted fisheye image comprises at least one target object; dividing the distorted fisheye image into a plurality of zones according to a distortion degree; determining a zone to which each of the at least one target object belongs; categorizing the at least one target object according to the zone to which each of the at least one target object belongs; and inputting the distorted fisheye image and a category to which each of the at least one target object belongs into the object identification neural network to train the object identification neural network.

Abstract: A method for generating training data includes: defining a corresponding category tag for an object model in a three-dimensional scenario; acquiring a plurality of corresponding scenario images by modifying scenario parameters of the three-dimensional scenario; rendering the object model to a monochromic material corresponding to the category tag of the object model; acquiring a semantic segmentation image corresponding to each scenario image based on the rendered object model; and storing each scenario image and the semantic segmentation image corresponding to the scenario image as a set of training data.

Abstract: A method for waking up a robot includes: acquiring sight range information when a voice command issuer issues a voice command; if the sight range information of the voice command issuer when issuing the voice command is acquired, determining, based on the sight range information, whether the voice command issuer gazes the robot when the voice command is issued; and determining that the robot is called if the voice command issuer gazes the robot.

Abstract: An actuator, a robot arm and a robot are disclosed. The actuator includes: a housing; a motor, including a motor stator and a motor rotor, wherein the motor stator is disposed on the housing, the motor rotor is rotatably connected to the housing, and the motor rotor covers the motor stator; a position encoder, disposed on the motor rotor; a motor driver, disposed on the housing, and electrically connected to the motor; a reducer, disposed on the housing, and parallelly disposed with the motor; and a transmission mechanism, connected to the motor rotor and the reducer respectively; wherein the reducer is configured to adjust a rotation speed output from the motor rotor.

Abstract: An audio-visual perception system includes an audio perception module and a visual perception module, respectively receiving sounds and images of a subject and converting them into audio and visual signals. At least one of the above two modules is a first perception module having more than one working mode. A processing and control module controls the first perception module to switch a working mode thereof based on the audio or visual signals received from one of the two above modules other than the first perception module. An audio-visual perception apparatus having the audio-visual perception system is also disclosed, which can be used as a robot control unit (RCU) mounted onto a robot, allowing a human-in-the-loop robot operator to visually and audibly monitor the subject in a surrounding of the robot. The RCU can switch between a RCU mode and a cell phone mode.

Abstract: A network path optimization method includes: in response to a network access request, computing and sending an optimal path having a path code and carrying a path parameter; adding a path tag to the optimal path based on a real path; determining a parameter variation between the optimal path and the real path based on the path parameter and the path tag; and updating the optimal path and the path parameter based on the parameter variation.

Abstract: A method for testing software includes: determining influencing factors which influence implementation of a target function of the software; constructing a test case set for each of the influencing factors; inputting the test case set corresponding to each of the influencing factors to the software; enabling the software to run the test case set; calculating an accuracy of each of the influencing factors against implementation of the target function of the software according to a running result of the test case set run by the software; determining, according to the accuracy achieved each of the influencing factors, whether a predetermined qualification condition is satisfied; determining that the software is tested to be qualified if the predetermined qualification condition is satisfied; and determining that the software is tested to be unqualified if the predetermined qualification condition is not satisfied.

Abstract: A route selection method based on hybrid resources, the route selection method being applied to a server, the server being communicably connected to a multi-node network, the multi-node network including at least two network nodes, wherein the method includes: constructing a directed graph for the multi-node network, and constructing a directed edge for each of the at least two network resources among the network resources if the at least two network resources are included between any two network nodes; and receiving node information of various network nodes, acquiring a delay weight value between any two network nodes under any network resource based on the node information, and assigning the delay weight value to a corresponding directed edge.