Abstract: A legged robot having a frame with a plurality of links in mechanical communication with plurality of brackets, the frame forming a front, back, top, bottom, and sides, legs in mechanical communication with one or more of the plurality of brackets, each leg having a knee motor, an abduction motor, and a hip motor, a computer module in mechanical communication with one or more of the plurality of brackets and in electrical communication with the legs, and a power module in mechanical communication with one or more of the plurality of brackets and in electrical communication with the legs and the computer module.

Abstract: A charging control system includes a lawn mower that includes a battery and performs a lawn mowing work while traveling autonomously, and a charging station for charging the battery. The lawn mower includes a superimposing unit for superimposing, on a charging current, a current indicating period information for defining a shutoff period of supply power to be supplied from the charging station. The charging station includes a current detector for detecting the charging current, an information acquisition unit for acquiring period information based on a detection result of the current detector, a switch for shutting off the supply power, and a shutoff controller for controlling the operation of the switch. The shutoff controller releases the shutoff of supply of power to the lawn mower based on the period information acquired by the information acquisition unit. Therefore, the power consumption of the lawn mower can be reduced.

Abstract: Provided is a medium storing instructions that when executed by one or more processors of a robot effectuate operations including: obtaining, with a processor, first data indicative of a position of the robot in a workspace; actuating, with the processor, the robot to drive within the workspace to form a map including mapped perimeters that correspond with physical perimeters of the workspace while obtaining, with the processor, second data indicative of displacement of the robot as the robot drives within the workspace; and forming, with the processor, the map of the workspace based on at least some of the first data; wherein: the map of the workspace expands as new first data of the workspace are obtained with the processor; and the robot is paired with an application of a communication device.

Abstract: A moving robot including: a lidar sensor to acquire terrain information; a memory to store node data nodes; and a controller to determine whether at least one open movement direction exists based on sensing data of the lidar sensor and the node data, to generate a new node in the node data and add the generated node to a node group, to determine any of the open movement directions as a movement direction, to control the robot to travels an area corresponding to the node group, to control a suction unit to suck foreign matter around the main body when traveling in the node group, to initialize the node group, to determine whether at least one node is to be updated, moving the robot to any one of the nodes to be updated, and to complete generation of a map.

Abstract: A robot system includes a robot arm, encoders configured to acquire position information of the robot arm, a first control section configured to execute control processing for controlling operation of the robot arm, and a second control section provided independently from the first control section and configured to transmit a position information request signal for requesting the position information to the encoders. The second control section transmits an interrupt signal to the first control section according to the transmission of the position information request signal. The first control section executes the control processing based on the interrupt signal and the position information output from the encoders based on the position information request signal.

Abstract: An autonomous robot moves materials in a warehouse or other industrial environment. It runs on an electric motor powered by a rechargeable battery. When its battery becomes depleted, it maneuvers to a nearby charger. It guides itself to the charger using visual cues, such as a target on or near the charger, until it establishes a good electrical connection with the charger. Proximity sensors on the charger and/or the autonomous robot determine if the autonomous robot is positioned properly; if so, the charger begins charging the autonomous robot's battery. While charging, the charger monitors the resistance of the electrical connection for open- or short-circuit conditions. It also monitors the status of the proximity sensors. If the charger detects an open-circuit or a short-circuit or that the autonomous robot has moved away from the charger, the charger stops charging.

Abstract: The present disclosure relates to a plurality of autonomous mobile robots. A plurality of autonomous mobile robots comprise a first mobile robot including an antenna configured to transmit and receive signals, and a second mobile robot including a first antenna and a second antenna disposed on a front area of a main body thereof to transmit and receive signals to and from the antenna of the first mobile robot. The second mobile robot comprises a control unit configured to determine a relative position of the first mobile robot using the signal received by the first antenna and the second antenna.

Abstract: Systems, apparatuses, and methods for rapid machine learning for floor segmentation for robotic devices are disclosed herein. According to at least one non-limiting exemplary embodiment, a robotic system is disclosed. The robotic system may comprise a neural network embodied therein capable of learning associations between color values of pixels and corresponding classifications of those pixels, wherein neural network is trained initially to identify floor and non-floor pixels within images. A user input may be provided to the neural network to further configure the neural network to be able to identify navigable floors and unnavigable floors unique to an environment without a need for additional annotated training images specific to the environment.

Abstract: A robot balance control method includes: obtaining force information associated with a left foot and a right foot of the robot; calculating a zero moment point of a center of mass (COM) of a body of the robot based on the force information; calculating a first position offset and a second position offset of the robot according to the zero moment point of the COM of the body; updating a position trajectory of the robot according to the first position offset and the second offset to obtain an updated position of the COM of the body; performing inverse kinematics analysis on the updated position of the COM of the body to obtain joint angles of the left leg and the right leg of the robot; and controlling the robot to move according to the joint angles.

Abstract: A robotic control system directs a robot to take an object from a human grasp by obtaining an image of a human hand holding an object, estimating the pose of the human hand and the object, and determining a grasp pose for the robot that will not interfere with the human hand. In at least one example, a depth camera is used to obtain a point cloud of the human hand holding the object. The point cloud is provided to a deep network that is trained to generate a grasp pose for a robotic gripper that can take the object from the human's hand without pinching or touching the human's fingers.

Abstract: A modular movable robot including a main body, a traveling unit mounted on a lower end of the main body, a module coupling plate which is mounted on an upper end of the main body and on which an object to be transferred is disposed on a top surface thereof, a port module coupled to the top surface of the module coupling plate to fix the object to be transferred, the port module being configured to provide module information to the module coupling plate, a body display unit extending from one end of the module coupling plate, a head display unit rotatably mounted on an upper end of the body display unit, and a control unit configured to receive the module information from the module coupling plate to control at least one of the body display unit or the head display unit on the basis of the received information.

Abstract: Provided is a method for controlling a robot cleaner, the method comprising: a preparatory step of dividing a cleaning target area input by an user into a plurality of to-be-cleaned regions and identifying a battery consumption required for cleaning each region; a determination step of determining whether the robot cleaner requires additional charging to clean the cleaning target area based on a current battery residual amount of the robot cleaner; upon determination that the additional charging is required, a selection step for selecting a first region, wherein the first region is defined as one combination selected from combinations of to-be-cleaned regions among the plurality of to-be-cleaned regions which are determined to be able to be cleaned using the current battery residual amount of the robot cleaner; and a first cleaning step of cleaning the first region.

Abstract: A mobile robot that includes a control system, a task execution system and a drive system, the control system configured to monitor the task execution system and drive system, wherein the control system comprises an error detection unit, the error detection unit configured to detect a first error in the task execution system and a second error in the drive system, and further configured to determine that a third error has occurred if it detects the first error and the second error at the same time.

Abstract: A switch-gear or control-gear system for medium or high voltage use includes an external housing containing the switch-gear or control-gear system, which is configured for unmanned operation and maintenance. The switch-gear or control-gear system is configured for unmanned operation and maintenance with a robotic system or manipulator and the robotic system or manipulator is provided with a camera system and an image recognition system. The robotic system is provided with a data network or an external data communication interface.

Abstract: The present disclosure discloses a biped robot and its moving method and apparatus. The method includes: calculating a motion state of each servo of legs of a biped robot according to an actual trajectory of the biped robot, and controlling the servo to rotate to the corresponding motion state. The scheme enables the biped robot to achieve flexible controls to the biped robot according to the received real-time external feedbacks.

Abstract: The embodiment of the present disclosure provides a robot control method, a robot and a storage medium. In the embodiment of the present disclosure, the robot determines a position when the robot is released from being hijacked based on relocalization operation; determines a task execution area according to environmental information around the position when the robot is released from being hijacked; and afterwards executes a task within the task execution area. Thus, the robot may flexibly determine the task execution area according to the environment in which the robot is released from being hijacked, without returning to the position when the robot is hijacked, to continue to execute the task, then acting according to local conditions is realized and the user requirements may be met as much as possible.

Abstract: Provided is a robot including main and peripheral brushes; a first actuator; a first sensor; one or more processors; and memory storing instructions that when executed by the one or more processors effectuate operations including: determining a first location of the robot in a working environment; obtaining, with the first sensor or another sensor, first data indicative of an environmental characteristic of the first location; adjusting a first operational parameter of the first actuator based on the sensed first data to cause the first operational parameter to be in a first adjusted state while the robot is at the first location; and forming or updating a debris map of the working environment based on data output by the first sensor or the another sensor configured to collect data indicative of an existence of debris on a floor of the working environment over at least one cleaning session.

Abstract: A heat dissipation device and a robot using the same are provided. The heat dissipation device comprises a porous material layer, a transporting tube and a liquid. The at least one porous material layer is disposed on a housing surface of a robot. The porous material layer has an evaporation surface and an accommodation space. The evaporation surface is disposed through and exposed from the housing surface. The evaporation surface and the accommodation space are in fluid communication with each other. The transporting tube is connected to the at least one porous material layer and in fluid communication with the accommodation space. The liquid is transported into the at least one accommodation space through the transporting tube and exposed from the evaporation surface. Thus, the liquid evaporates at the evaporation surface to reduce a temperature of the housing surface of the robot via convection and evaporation.

Abstract: The present disclosure relates to a method, device and computer readable storage medium for presenting an emotion. The method for presenting the emotion includes obtaining a first emotion presentation instruction, wherein the first emotion presentation instruction includes at least one first emotion presentation modality and at least one emotional style, and the at least one first emotion presentation modality includes a text emotion presentation modality; and presenting an emotion corresponding to one or more of the at least one emotional style according to each of the at least one first emotion presentation modality. The present disclosure can realize text-based multi-modal emotion presentation modes, and thus user experience can be improved.

Abstract: A processor-implemented posture determination method includes: estimating a rotational acceleration of a timepoint based on an angular velocity measured by a first sensor at the timepoint and a determined center of rotation of a previous timepoint; correcting an acceleration measured by a second sensor at the timepoint based on the rotational acceleration; and determining a center of rotation of the timepoint and a posture of the timepoint based on the corrected acceleration and an estimated posture of the timepoint.

Abstract: A cleaner performing autonomous traveling includes a main body, first and second cameras photographing the periphery of the main body, and a controller controlling the first and second cameras to capture an image according to preset order, wherein a direction in which the first camera is directed and a direction in which the second camera is directed form a predetermined angle, and the controller generates three-dimensional (3D) coordinate information related to an object located near the main body using images obtained in the first and second cameras.

Abstract: A computing device receives a setup command and signals mobile robots to move sensor targets into positions within a predetermined range of a turntable. Each mobile robot may be coupled to a sensor target. Once the sensor targets are moved into the positions, calibration may be initiated, in which a vehicle is rotated using the turntable, and sensors coupled to the vehicle are calibrated based on detection of the sensor targets. The computing device may signal the mobile robots to adjust the sensor targets as needed, or, after calibration, to move into storage or charging positions.

Abstract: The disclosed embodiments disclose methods, apparatuses, systems, devices and computer-readable storage media for processing speech signals. The method comprises: acquiring a real-time image by using an image capturing device, performing facial recognition by using the real-time image, and detecting a period during which a target user makes speech sounds based on a facial recognition result; locating a sound source in an audio signal received by a microphone array, and determining the orientation information of a sound source in the audio signal; and based on the period during which the target user in the real-time image makes the speech sounds and the orientation information of the sound source, performing a speech sound start and end point analysis to determine start and end time points of the speech sounds in the audio signal.

Abstract: A walking state measurement device according to the present invention includes: at least one memory storing a set of instructions; and at least one processor configured to execute the set of instructions to: estimate a floor reaction force by use of at least either of motion data and lower limb vertical load data of a walker, and outputting the floor reaction force as floor reaction force data; and calculate a walking state of the walker by use of at least either of the motion data and the floor reaction force data, and outputting the walking state.

Abstract: A mobile robot including an image pickup unit, further includes an accumulation unit configured to accumulate imaging data taken in the past, a reception unit configured to receive designation of a spatial area from a remote terminal, and a processing unit configured, when it is possible to shoot the spatial area received by the reception unit by the image pickup unit, to perform shooting and transmit obtained imaging data to the remote terminal, and when the shooting is impossible, to transmit imaging data including an image of the spatial area accumulated in the accumulation unit to the remote terminal and start a moving process in order to shoot the spatial area by the image pickup unit.

Abstract: A vacuumed material collection station for receiving vacuumed material from a vacuum cleaning apparatus includes a vacuumed material collection container and an interface for connecting the vacuum cleaning apparatus to the vacuumed material collection station. The vacuumed material collection station comprises a receptacle space for receiving a filter chamber of a vacuum cleaning apparatus connected to the vacuumed material collection station and a feed device for feeding the filter chamber into the receptacle space. The receptacle space is designed for completely encompassing the filter chamber and/or at the most not encompassing a chamber side facing the interface with the vacuum cleaning apparatus. The receptacle space forms a partial volume within the housing of the vacuumed material collection station, and the feed device is designed for removing the filter chamber from the vacuum cleaning apparatus and displacing the filter chamber into the receptacle space.

Abstract: Provided is a drive device that can remove the influence of static friction by driving two drive axes with three drive units. A drive device includes: a first drive unit; a second drive unit; a third drive unit; a first differential unit connected to the first drive unit and the second drive unit; a second differential unit connected to the second drive unit and the third drive unit; and a control unit that controls the first to third drive units. The control unit controls the second drive unit at a constant speed, and controls a speed of each of the first drive unit and the third drive unit relative to that of the second drive unit.

Abstract: A control device includes a control unit which executes a control force to a movable unit according to an output of a force detection unit. The control unit executes a stop control of the movable unit when a predetermined stop condition is satisfied. The stop control includes a second control which continues the force control to control the movable unit when the stop condition is satisfied during the execution of a first control including a force control.

Abstract: A cleaner includes a cleaner body, a power supply including a first battery and a second battery that are accommodated in the cleaner body, and a power supply circuit configured to operate in a charge mode for receiving power from the outside to recharge the first and second batteries or in a discharge mode for supplying the power recharged in the first and second batteries to a load, a charging terminal connected to an external charging stand and configured to supply direct current (DC) power to the first and second batteries in the charge mode, and a controller configured to control an operation of the power supply in the discharge mode and the charge mode.

Abstract: The present invention relates to a moving robot and a control method thereof, and includes a sensor unit configured to detect an obstacle located in a traveling direction; a camera configured to photograph the obstacle, when the obstacle is detected by the sensor unit; a controller configured to control a certain operation to be performed in accordance with the obstacle. The controller analyzes a plurality of image data of the obstacle inputted from the camera to determine whether the obstacle can be identified and filters the image data, transmits the filtered image data among the plurality of image data to the server through the communication unit, and controls the traveling unit in accordance with obstacle information received from the server. Hence, by transmitting only recognizable image, unnecessary data transmission is reduced, and accordingly, transmission traffic is reduced and the load of image processing of the server is reduced.

Abstract: A cleaner includes a cleaner body, a power supply including a first battery and a second battery that are accommodated in the cleaner body, and a power supply circuit configured to operate in a charge mode for receiving power from the outside to recharge the first and second batteries or in a discharge mode for supplying the power recharged in the first and second batteries to a load, a charging terminal connected to an external charging stand and configured to supply direct current (DC) power to the first and second batteries in the charge mode, and a controller configured to control an operation of the power supply in the discharge mode and the charge mode.

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 includes: executing judgment processing for judging whether a site to carry out a first task assigned to a first robot and a site to carry out a second task assigned to a second robot are likely to overlap each other; executing comparison processing for comparing first end time with second end time when the sites to carry out the first task and the second task are likely to overlap each other; and executing determination processing for selecting the first task order when the first end time is earlier than the second end time, and selecting the second task order when the second end time is earlier than the first end time.

Abstract: The present invention makes it possible to appropriately grasp a stop cause when a vehicle stops. An ECU 5, which controls a vehicle including wheels and a vehicle body connected to the wheels includes: a wheel stop detection unit 138 that detects a stop of the wheels; a vehicle body stop detection unit 133 that detects a stop of the vehicle body; and a stop cause determination unit 141 that determines a stop cause of the vehicle based on a stop timing of the wheels detected by the wheel stop detection unit 138 and a stop timing of the vehicle body detected by the vehicle body stop detection unit 133. The stop cause determination unit 141 may determine that the stop cause is contact of the vehicle body with an obstacle when the stop timing of the vehicle body is earlier than the stop timing of the wheels.

Abstract: There are a biped robot gait control method and a biped robot, where the method includes: obtaining six-dimensional force information, and determining a motion state of two legs of the biped robot; calculating a ZMP position of each of two legs of the biped robot; determining a ZMP expected value of each of the two legs in real time; obtaining a compensation angle of an ankle joint of each of the two legs of the biped robot by inputting the ZMP position, a change rate of the ZMP position, the ZMP expected value, and a change rate of the ZMP expected value to an ankle joint smoothing controller so as to perform a close-loop ZMP tracking control on each of the two legs; adjusting a current angle of the ankle joint of each of the two legs of the biped robot in real time; and repeating the forgoing steps.

Abstract: A collision avoidance method and system for a mobile robot crossing a road. When a mobile robot approaches a road, it senses road conditions via at least one first sensor, and initiates road crossing if the road conditions are deemed suitable for crossing. As it crosses the road, the mobile robot senses, via at least one second sensor, a change in the road conditions indicating the presence of at least one hazardous moving object. In response to determining that at least one hazardous object in present, the mobile robot initiates a collision avoidance maneuver. A mobile robot configured to avoid collisions while crossing a road includes: at least one first sensor configured to sense road conditions, at least one second sensor configured to sense road conditions, and a processing component configured to carry out one or more collision avoidance maneuvers.

Abstract: A robot leg (125) comprises an upper link (101) and a lower link (111). The upper link (101) operates nominally in a first vertical plane, for example the sagittal plane, while the lower link (111) operates nominally in a second vertical plane, nominally orthogonal to the first plane, for example the coronal plane. The leg (125) may also comprise a twist joint in the knee, and may comprise four-bar linkages (102a-b, 103a-d, 112a-b, 113a-d), such that the foot (106) stays parallel to the hip (102a). The leg (125) may be used in a robot to allow the construction of a robot capable of three dimensional movement, using a small number of actuators per leg.

Abstract: A method of conducting preventative maintenance on a robotic surgical system is provided. The method includes sensing an audio output generated by one or more components of a robotic surgical system with a sensor coupled to the robotic surgical system, converting the audio output into audio output data, comparing the audio output data to a predefined audio data stored in a memory device that is coupled to the robotic surgical system, and selectively outputting a preventative maintenance signal based on a comparison of the audio output data and the predefined audio data.

Abstract: The invention relates to a system to carry out a floor related action. The system comprises an animal enclosure for detaining at least one animal and provided with an enclosure floor surface, a first autonomous vehicle configured to navigate over the floor surface to carry out the floor related action, and a feed providing device to provide feed to the animal. The system comprises a communication signal configured to transmit a communication signal representative for an actual or planned feeding action of the feed providing device to the first vehicle, which action influences the position of animals with the animal enclosure. In order to move the first vehicle more efficiently over the stable floor, in particular to avoid interference with animals on the stable floor, the first vehicle is capable to adapt its navigation based on the communication signal representative for the actual or planned feeding action.

Abstract: A load detection device capable of preventing deterioration of the accuracy of a load detection with the lapse of time is provided. A first exemplary aspect is a load detection device, including: a load detection part including a curved surface; an application member comprising a flat surface; and a transmission member located between the load detection part and the application member. The curved surface of the load detection part and a first surface of the transmission member come into point contact with each other, and the flat surface of the application member and a second surface opposite to the first surface of the transmission member come into surface contact with each other.

Abstract: A transfer robot includes one arm, another arm, and a motor. The one arm has a first connection portion. The other arm has a second connection portion that is connected to the first connection portion of the one arm via a shaft such that the other arm is rotatable relatively with respect to the one arm around a shaft axis of the shaft. The motor is provided inside the first connection portion of the one arm. The motor includes a rotor rotatable around the shaft axis to rotate the one arm or the other arm around the shaft axis.

Abstract: In a method for operating a self-traveling floor treatment apparatus, a recording device of the floor treatment apparatus records a recording of an environment of the floor treatment apparatus, which concerns a time period, and the recording is displayed for a user of the floor treatment apparatus on a screen. In order to allow correction of error conditions, the recording is stored and, in case of a defined environmental event and/or apparatus condition of the floor treatment apparatus, a time-defined partial sequence is subsequently extracted from the stored recording and displayed on the screen.

Abstract: In one aspect, a system for operating an agricultural harvester may include a sensor assembly configured to detect a parameter indicative of an operating line of the harvester. The system may also include a controller configured to monitor the operating line of the harvester based on measurement signals received from the sensor assembly when the harvester is operated in a first operating mode. The controller may also be configured to determine a differential between the operating line and a predetermined guidance line of the harvester. Furthermore, the controller may be configured to update a stored correction value based on the determined differential. Additionally, when the harvester is switched from the first operating mode to a second operating mode, the controller may be configured to adjust a location of the predetermined guidance line based on the stored correction value.

Abstract: Disclosed are a method and device for selecting a to-be-cleaned area.

Abstract: A smartphone or other mobile computer device, general purpose or specialized, wherein the smartphone device is configured to actively control the configuration of one or more bladders, compartments, chambers or internal sipes and one or more sensors located in either one or both of a sole or a removable inner sole insert of the footwear of the user and/or located in an apparatus worn or carried by the user, glued unto the user, or implanted in the user. The one or more bladders, compartments, chambers, or sipes, and one or more sensors are configured for computer control. A sole and/or a removable inner sole insert for footwear, including one or more bladders, compartments, chambers, internal sipes and sensors in the sole and/or in a removable insert; or on an insole; all being configured for control by a smartphone or other mobile computer device, general purpose or specialized.

Abstract: A combined robot includes a self-moving robot and a functional module, in which the functional module is detachably combined into the self-moving robot through a connecting piece. Driving wheels and a driven wheel are disposed at a bottom of a machine body of the self-moving robot. By taking an advancing direction when the self-moving robot operates as a forward direction, the driving wheels are located on a left side and a right side of the bottom of the machine body. The driven wheel is located at a front end or a rear end of the bottom of the machine body. A control center is disposed in the combined robot and controls the combined robot to operate. One end away from the driven wheel of the bottom of the machine body of the self-moving robot is a supporting end, and floating supporting mechanisms are disposed at the supporting end.

Abstract: A robotic cleaning device having an inertia measurement unit and a controller. The inertia measurement unit is arranged to sense a displacement of the robotic cleaning device and the controller is arranged to determine a characteristic of the displacement of the robotic cleaning device, and to set the robotic cleaning device in an operational mode being associated with the determined characteristic of the displacement.

Abstract: The present disclosure provides a robot distance measuring method and apparatus as well as a robot using the same. The method includes: obtaining a plurality of relative position parameters of a robot from a plurality of ranging sensors; determining an installation distance between each two of the ranging sensors based on the plurality of relative position parameters; determining a sum of the installation distance of each looping arrangement of the plurality of ranging sensors based on the installation distance between each two of the ranging sensors; and enabling the plurality of ranging sensors sequentially to perform obstacle ranging according to a preset looping rule. Since the adjacent ranging sensors are avoided to range simultaneously or sequentially, the interference of the adjacent ranging sensors can be minimized, the accuracy of measuring the distance of the surrounding obstacles can be improved, thereby improving the navigation performance of the robot.

Abstract: Provided herein a vacuum cleaner capable of effectively escaping from a situation where driving wheels are in an idling state. The vacuum cleaner includes a main casing, driving wheels, a control unit and an idling detection part. The driving wheels enable the main casing to travel. The control unit controls the driving of the driving wheels to make the main casing autonomously travel. The idling detection part detects that the driving wheels are in an idling state. In the case where the idling detection part detects that the driving wheels are in an idling state, the control unit controls the operation of the driving wheels so as to, after the operation to make the main casing retreat by a certain distance, repeat consecutively for a plurality of times the operation to make the main casing turn in a specified one direction and advance by a specified distance.

Abstract: A toy construction system comprising toy construction elements, comprising coupling means for releasably interconnecting the toy construction elements, one or more marker construction elements comprising such coupling means and each having a visual appearance recognizable by an image processing means, and a data processing system adapted to process a captured image of a toy construction model constructed from the toy construction elements to detect at least a presence of at least one of the marker construction elements within the captured image, and responsive to the detected marker construction element, generate a computer-generated image, wherein the marker construction element comprises a visually detectable feature and a movable element movable between a first and a second position, wherein the movable element, when positioned in the first position, causes the visually detectable feature to be visible and, when positioned in the second position, causes the visually detectable feature to be obstructed from