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: The present disclosure relates to robot technology, which provides a robot pose estimation method as well as an apparatus and a robot using the same. The method includes: obtaining, through an inertial measurement unit, initial 6DoF pose data; performing a first correction on the initial 6DoF pose data based on pose data obtained through an auxiliary sensor to obtain corrected 6DoF pose data; obtaining, through a 2D lidar sensor disposed on a stable platform, 3DoF pose data; and performing a second correction on the corrected 6DoF pose data based on the 3DoF pose data to obtain target 6DoF pose data. In this manner, the accuracy of the pose data of the robot is improved, and the accurate pose estimation of the robot is realized.

Abstract: A method and apparatus for controlling a robot is provided. In this robot, direct teaching can be performed while updating a position command on the basis of an applied external force. In the method and apparatus, a proximity region is set inside a boundary of an operation-allowed range of the robot, the proximity region being indicative of a proximity of the boundary. Stored is an external force applied when a monitoring point provided in the robot reaches the proximity region as a reference external force. And performed is comparing the reference external force with a current external force when a current position of the monitoring point is in the proximity region, to thereby determine a direction that facilitates movement away from the proximity region.

Abstract: A hand controller for enabling a user to perform an activity and method for controlling a robotic arm is provided. The hand controller includes a bar with a grip and a plurality of motors to provide a force feedback to the user in response to the movement of the plurality of mechanical arms. The method involves receiving input corresponding to the manipulation of a bar and providing a force feedback in response to the movement of the plurality of mechanical arms.

Abstract: A mobile robot includes a communication unit that communicates with another mobile robot, a sensing unit for sensing the other mobile robot existing in a detection area encompassing a predetermined projected angle with respect to the front of a main body of the mobile robot, and a control unit configured for rotating the main body so that the other mobile robot is sensed in the detection area. The communication unit transmits a control signal configured to cause the other mobile robot to travel in a linear direction by a predetermined distance, to the other mobile robot when the other mobile robot is present in the detection area.

Abstract: Disclosed is a master robot for controlling at least one slave robot. The master robot includes a communicator that communicates with the slave robot or a mobile terminal, at least one sensor, an inputter that inputs an image signal or an audio signal, and a controller that creates a space map corresponding to a predetermined space in which the master robot and the slave robot are located on the basis of information sensed by the sensor or information inputted through the inputter. Accordingly, a master robot equipped with artificial intelligence and a 5G communication module can be provided.

Abstract: An upper limb motion support apparatus and an upper limb motion support system which are capable of significantly improving the enhancement of an operator's work efficiency and the reduction of their workload are proposed. A controller which causes an articulated arm and an end effector to perform three-dimensional motion according to the operator's intention based on a biological signal acquired by a biological signal detection unit causes the articulated arm and the end effector to perform cooperative motion in conjunction with the operator's upper limb motion by referring to content recognized by an upper limb motion recognition unit.

Abstract: Embodiments generally relate to determining traffic congestion patterns. In some embodiments, a method includes identifying congestion events for each road of a plurality of roads in a road network, where each congestion event indicates a drop in average vehicle speed below a predetermined speed threshold for a particular road in the road network, and where the congestion events span a predetermined time period. The method further includes determining local clusters of the congestion events based on one or more road condition parameters, where each local cluster defines a local congestion pattern for a particular road of the plurality of roads in the road network. The method further includes grouping the local clusters into one or more global clusters based on the one or more road condition parameters, where the global clusters define global congestion patterns in the road network.

Abstract: A machine tool is disclosed which can suppress resonance of an in-machine robot even when vibration occurs during machining of a workpiece. Vibration of the in-machine robot is detected by a vibration sensor of the in-machine robot. When the vibration of the in-machine robot becomes greater than or equal to a threshold during machining of the workpiece, a controller changes a natural frequency of the in-machine robot by exchanging an end effector of the in-machine robot or by changing an orientation of the in-machine robot, to thereby suppress resonance of the in-machine robot.

Abstract: Embodiments of the present invention provide automated robotic system identification and stopping time and distance estimation, significantly improving on existing ad-hoc methods of robotic system identification. Systems and methods in accordance herewith can be used by end users, system integrators, and the robot manufacturers to estimate the dynamic parameters of a robot on an application-by-application basis.

Abstract: A method for modeling a robot simplified for stable walking control of a bipedal robot provides a robot model that is simplified as a virtual pendulum model including a virtual body, two virtual legs connected to the body at a virtual pivot point (VPP) that is set at a position higher than the center of mass (CoM) of the body, and virtual feet connected to the two legs, respectively, to step on the ground. A ground reaction force, which acts on the two legs, acts towards the VPP, thereby providing a restoring moment with respect to the CoM such that stabilization of the posture of the body naturally occurs.

Abstract: Provided is an autonomous moving body configured to move along a planned movement path to execute a given task, including: an external sensor configured to recognize another autonomous moving body given another task and an operation state of the another autonomous moving body; an overtaking determination unit configured to determine, when it is recognized by the external sensor that the another autonomous moving body moves along the movement path, whether to overtake the another autonomous moving body; and a movement control unit configured to control a moving unit based on the determination of the overtaking determination unit.

Abstract: Embodiments generally relate to determining traffic congestion patterns. In some embodiments, a method includes identifying congestion events for each road of a plurality of roads in a road network, where each congestion event indicates a drop in average vehicle speed below a predetermined speed threshold for a particular road in the road network, and where the congestion events span a predetermined time period. The method further includes determining local clusters of the congestion events based on one or more road condition parameters, where each local cluster defines a local congestion pattern for a particular road of the plurality of roads in the road network. The method further includes grouping the local clusters into one or more global clusters based on the one or more road condition parameters, where the global clusters define global congestion patterns in the road network.

Abstract: A robot system includes circuitry. The circuitry may be configured to acquire teaching position data including a plurality of teaching positions arranged in time series based on the demonstration data of the operator. The circuitry may be further configured to generate thinned position data obtained by removing at least one of the teaching positions from the teaching position data. The circuitry may be further configured to generate a position command based on the thinned position data. The circuitry may be further configured to operate the work robot based on the position command.

Abstract: Methods, systems, and computer programs stored on computer storage devices, for coordinating movements of robots are disclosed. One of the methods includes, for each robot in a group of robots, identifying a set of tasks assigned to the robot and generating a plurality of candidate motion plans. The method further includes, for each candidate motion plan: (i) generating a 3D model that represents a volume of space through which the robot would move in executing the sequence of motions represented by the candidate motion plan, and (ii) determining a score for the candidate motion plan. The method further includes determining conflicts between candidate motion plans of different robots, selecting a motion plan from the candidate motion plans based on the score for the selected motion plan and the conflicts, and providing the selected motion plans for execution by the group of robots.

Abstract: In one embodiment, a computing system receives sensor data from one or more sensors of a vehicle. The computing system determines a metric associated with the vehicle based on the received sensor data. The computing system determines, based on the metric, a length of a transmission cycle of a communication network of the vehicle. The transmission cycle comprises one or more scheduled time periods dedicated for transmitting data from respective first nodes in the communication network. The computing system configures the communication network of the vehicle based at least in part on the length of the transmission cycle to adjust respective occurrence frequencies of the scheduled time periods over multiple instances of the transmission cycle.

Abstract: Movement guidance information for performing traveling guidance for a vehicle is requested to a guidance information delivering server device based on an area update table and an area identification table for managing an update state of map information in a communication terminal, and traveling guidance for the vehicle is performed based on the movement guidance information delivered from the guidance information delivering server device in response to the request.

Abstract: Methods, apparatus, and computer-readable media for determining and utilizing human corrections to robot actions. In some implementations, in response to determining a human correction of a robot action, a correction instance is generated that includes sensor data, captured by one or more sensors of the robot, that is relevant to the corrected action. The correction instance can further include determined incorrect parameter(s) utilized in performing the robot action and/or correction information that is based on the human correction. The correction instance can be utilized to generate training example(s) for training one or model(s), such as neural network model(s), corresponding to those used in determining the incorrect parameter(s). In various implementations, the training is based on correction instances from multiple robots. After a revised version of a model is generated, the revised version can thereafter be utilized by one or more of the multiple robots.

Abstract: A mechanical eyeball includes an outer housing shaped as an ocular surface configured to rotate about a first rotational axis and a second rotational axis that intersect at a fixed center point. The outer is housing is coupled to a mechanical assembly, and the mechanical assembly is contained within a volume associated with the mechanical eyeball. The mechanical assembly can include a stationary gear train and rotatable components that rotate relative to the gear train. The rotatable components are configured to cause rotation of the outer housing about one or more rotational axes. The volume may be substantially the same volume of a human eye. The mechanical assembly is coupled to one or more drivers configured to actuate rotation of the outer housing.

Abstract: A walking control method of a robot is provided. The method includes receiving a walking command of the robot including a link device having a plurality of links that correspond to both lower limbs. In response to receiving the walking command, implementing walking of the robot by providing torque to the link device to move a first lower limb is moved. In a double stance state where foot ends of the both lower limbs are simultaneously in contact with ground while the lower limb to be moved is changed, a driving force is generated in the double stance by adjusted the torque of the drive device to virtually move the foot ends of the both lower limbs by a predetermined stable distance in an opposite direction to a walking direction.