A robot includes: a light detection and ranging (LiDAR) sensor; a plurality of directional microphones; and at least one processor configured to: identify, based on sensing data obtained through the LiDAR sensor, an object in a vicinity of the robot, identify, based on the type of the object, a weight to apply to an audio signal received through a directional microphone corresponding to a location of the object from among the plurality of directional microphones, obtain context information of the robot based on the sensing data, identify, based on the context information, a pre-processing model corresponding to each directional microphone of the plurality of directional microphones, apply the weight to an audio signal received through the directional microphone corresponding to the location of the object among a plurality of audio signals received through the plurality of directional microphones, obtain a plurality of pre-processed audio signals by inputting the audio signal to which the weight has been applied, and the remaining audio signals into the pre-processing model corresponding to the respective directional microphone , and perform voice recognition based on the plurality of pre-processed audio signals.

Aspects include a robotic device for inspection of components of a belt conveyor comprising a mobile platform and a robotic arm having a first end coupled to the mobile platform and a second end, the robotic arm configured to guide the second end to contact at least one of the components of the belt conveyor. Further included is a method for inspecting components of a belt conveyor using a robotic device, including: obtaining temperature and/or noise data of at least one of the components of the belt conveyor; and, if the data are outside a range, then: driving a second end a robotic arm of the robotic device for contacting at least one of the components; and obtaining vibration data from at least one of the components.

A method for examining a robot apparatus which includes a driving source configured to drive a joint, the position and orientation of which are controlled based on trajectory data determined in advance for a normal motion. The examination method includes generating examination motion data for driving a joint as an examination target under a driving speed that causes the examination target joint to resonate and causing the examination target joint to pass through a path based on the trajectory data. A resonance amplitude of the joint is acquired based on the examination motion data.

A moving robot includes a main body which forms a space therein, a noise generating member which is disposed inside the main body and generates a noise, an inner housing and an outer housing which surround the main body, and two or voice recognition members which are disposed in the housing and are disposed to be separated from each other, and a noise recognition member which recognizes a noise. The voice recognition members are disposed on a side opposite to the noise generating member based on a central point and disposed to be separated from each other along an outer peripheral surface of the housing. Accordingly, a voice command is determined by a difference of the voice data acquired by the two voice recognition members separated from each other and noise data recognized by the noise recognition member to improve voice recognition efficiency.

A method for detecting a ground attribute of a legged robot includes obtaining a collision audio of a foot of the legged robot with a ground; and detecting a workable level attribute of the ground in a working environment of the legged robot according to the collision audio. The sound of the collision between the foot of the robot and the ground is collected, and the workable level attribute of the ground in the working environment of the legged robot is detected based on the sound, so that the operable level attribute can be effectively used to control the legs of the legged robot. On the one hand, the motion noise of the legged robot can be reduced, and on the other hand, the power consumption of the legged robot can be reduced, thereby increasing its range of motion.

Methods and systems for training a robotic manipulator. The system may include one or more sensor devices and a robotic manipulator for executing an item grasping strategy to grasp an item. The system may further evaluate the item grasping strategy to determine whether the strategy was successful.

Methods and systems for assessing a robotic grasping technique. The system in accordance with various embodiments may include a warehouse management system for retrieving and storing items, a robotic manipulator for grasping an item, and analysis module configured to receive data regarding a first grasp attempt by the robotic manipulator and analyze the received data to determine whether the robotic manipulator successfully grasped the item.

Touch events can be detected using an ultrasound input device coupled to a surface, such as a surface of a piece of furniture or electronic device. The ultrasound input device can generate ultrasonic waves in the surface, the reflections of which can be measured by the ultrasound input device. When a touch is made to the surface (e.g., opposite the ultrasound input device), the physical contact can absorb some of the energy of the outgoing ultrasonic waves (e.g., the originally transmitted wave and any subsequent outgoing reflections). Energy measurements associated with the measured reflections can thus be used to identify touch events. Various techniques can be used to make the energy measurements and reduce identification of false touch events.

A robot includes a main casing, a first spherical cap and a second spherical cap, and a shaft linking the spherical caps. The robot further includes a display, a first driving mechanism causing the first and second spherical caps to be rotated by the shaft, and a second driving mechanism that causes the main casing to be rotated. The robot also includes a control circuit and an electric power source, charged by electric power from an external charger. If the remaining electric power of the electric power source is lower than or equal to a predetermined value, the second driving mechanism is controlled to stop rotation of the main casing, and the first driving mechanism is controlled to switch a rotational direction of the first spherical cap and the second spherical cap, causing the display to be reciprocally moved in a vertical direction.

A vacuum clamp inspection system comprises a rigid structure; a sensor system mounted relative to the rigid structure; a calibration fixture mounted on the table; and a vacuum clamp configured to provide at least one of a location and a pose of a component relative to the calibration fixture.