Systems and methods for detecting a waste receptacle, the system including a camera for capturing an image, a convolutional neural network, and processor. The convolutional neural network can be trained for identifying target waste receptacles. The processor can be mounted on the waste-collection vehicle and in communication with the camera and the convolutional neural network configured for using the convolutional neural network. The processor can be configured for using the convolutional neural network to generate an object candidate based on the image; using the convolutional neural network to determine whether the object candidate corresponds to a target waste receptacle; and selecting an action based on whether the object candidate is acceptable.

Systems, devices, and methods for controlling a robot. Some methods include, in response to determining that an object enters a reachable area of the robot, triggering a first sensor to sense a movement of the object; determining first position information of the object based on data received from the first sensor; determining second position information of the object based on second data received from a second sensor; and generating a first prediction of a target position at which the object is operated by the robot. In this way, the robot can complete an operation for the object on the AGV within a limit operation time during which the AGV passes through the reachable area of the robot. Meanwhile, by collecting the sensing data from different sensor groups, a target position at which the object is handled by the robot may be predicted more accurately.

There is disclosed a stretchable sensor system for measuring deformation of an elastomer, the stretchable sensor system comprising at least one magnet; at least one magnetic sensor, each having a sensor output; and a controller, wherein the at least one magnet is/are fixed to the elastomer at a respective first location or plurality of locations and the at least one magnetic sensor is/are fixed to the elastomer at a respective second location or plurality of locations, such that the or each magnetic sensor is located in magnetic proximity to a respective said magnet, and wherein the controller is operable: to receive sensor data from the sensor output of the or each magnetic sensor; to process the received sensor data in dependence on the first and second locations or plurality of locations to determine a positional relationship between the or each magnet and the respective magnetic sensor; and to compute a deformation of the elastomer in dependence on the determined positional relationship between the or each magnet and the respective magnetic sensor. The present invention has particular application to soft robotics and closed loop control thereof.

Disclosed are a lawn mower robot and a control method for same. A lawn mower robot and a control method for same according to an embodiment of the present invention can sense height information about the height between a lawn and the lower side of the lawn mower robot. The sensed height information is used as supporting data for calculating whether the lawn mower robot has deviated from a preset travel path, as well as the deviation direction. Accordingly, even when a separate sensing means is not provided, whether the lawn mower robot has deviated from the preset travel path is calculated using the height information about the height from the ground, and thus the lawn mower can be returned to the preset travel path.

A computing system including a processing circuit in communication with a robot and a camera having a field of view. The processing circuit obtains image information based on the objects in the field of view and a loading environment, the loading environment which includes loading areas, an object queue, and a buffer zone. The computing system is configured to use the obtained image information in motion planning operations for the retrieval and placement of objects from the object queue into the loading environment. Pallets provided within the loading environment (i.e., within the loading areas) are dedicated to receiving objects having corresponding object type identifiers. The computer system further uses the image information to determine the fill status of pallets existing within the loading environment, and whether new pallets need to be brought into the loading environment and/or swapped out with existing pallets to account for future planning and placement operations.

This application relates to an autonomously navigating robot. In one aspect, the robot includes an end effector configured to measure a person's body temperature and, when the body temperature exceeds a standard fever temperature, activate a chatbot to check symptoms of Covid-19. The robot may also include a manipulator configured to align the end effector with the person's forehead. The robot may further include a mobile robot configured to detect the person and move the end effector and the manipulator to a position where the person is located by performing autonomous navigation.

An optical device includes: a substrate having a first surface, and a second surface opposite of the first surface; a plurality of surface emitting laser elements provided on the first surface of the substrate and configured to emit light in a direction intersecting the first surface; a plurality of optical elements disposed on the second surface so as to respectively correspond to the plurality of surface emitting laser elements; and an anti-reflection structure between the substrate and the plurality of optical elements.

Disclosed herein are a method of localization by synchronizing multi sensors and a robot implementing the same. The robot according to an embodiment includes a controller that, when a first sensor acquires first type information, generates first type odometry information using the first type information, that, at a time point when the first type odometry information is generated, acquires second type information by controlling a second sensor and then generates second type odometry information using the second type information, and that the robot by combining the first type odometry information and the second type odometry information.

The robot hand holds a wire harness having a long harness main body and a connector connected to an end of the harness main body. The robot hand includes a fixed holding portion which holds the harness main body a vicinity of the end thereof, a pressing portion movable relative to the fixed holding portion in a longitudinal direction of the harness main body held by the fixed holding portion, and a driving unit which moves the pressing portion in a direction away from the fixed holding portion such that the pressing portion presses the connector outwardly in the longitudinal direction of the harness main body.

Provided is a robot including a microphone configured to acquire a sound signal corresponding to a sound generated near the robot, a camera, an output interface including at least one of a display configured to output a wake-up screen or a speaker configured to output a wake-up sound when the robot wakes up, and a processor configured to recognize whether the acquired sound includes a voice of a person, activate the camera when the sound includes a voice of a person, recognize whether a person is present in an image acquired by the activated camera, set a wake-up word recognition sensitivity based on a recognition result as to whether a person is present, and recognize whether a wake-up word is included voice data of a user acquired through the microphone based on the set wake-up word recognition sensitivity.