Abstract: An apparatus for labeling support structures includes: a chassis having a locomotive assembly; an effector assembly having a first end coupled to the chassis and a second end movable relative to the chassis; a label modification unit at the second end of the effector assembly, the label modification unit including an image sensor; and a controller coupled to the locomotive assembly, the effector assembly and the label modification unit, the controller configured to: obtain label modification data defining a location of a low powered display relative to a reference feature on a support structure for modifying content displayed by the display; control the locomotive assembly to travel to the support structure; detect the reference feature via image data captured at the image sensor; control the effector assembly to place the label modification unit at the location; and control the effector assembly and the label modification unit to modify the content.

Abstract: Automatic calculation of a trajectory by taking the interference with an obstacle into account may be performed by calculating trajectory information representing a trajectory on which (i) the picking hand picks, on the first position, the work with a posture associated with the first position included in the first combination; and (ii) the picking hand arranges, on the second position, the work with a posture associated with the second position included in the first combination, and determining whether an interference is present or absent on the trajectory represented by the trajectory information calculated in the calculating a trajectory.

Abstract: A method and system of visually communicating navigation instructions can use translational and rotational arrow cues (TRAC) defined in an object-centric frame while displaying a single principal view that approximates the human's egocentric view of the actual object. A visual guidance system and method can be used to pose a physical object within three-dimensional (3D) space. Received pose data (402) indicates a current position and orientation of a physical object within 3D space, such that the pose data can provide a view of the physical object used to generate a virtual view of the physical object in 3D space. At least two of six degrees of freedom (6DoF) error can be calculated (404) based on a difference between the current position of the physical object and a target pose of the physical object.

Abstract: Unmanned ground vehicles configured for compact manipulator stowing are disclosed. In some examples, an unmanned ground vehicle includes a main body and a drive system supported by the main body. The drive system includes right and left driven track assemblies mounted on right and left sides of the main body. A manipulator arm is pivotally coupled to the main body and configured to extend from a stowed position to an extended position, and the manipulator arm in the stowed position is contained entirely within a geometric volume of the right and left driven track assemblies.

Abstract: A manipulator system includes at least one manipulator and a control device assigned to the manipulator; and at least one mobile operating device for controlling the at least one manipulator. In addition, an electronic display device is provided, which is arranged to display at least one optically readable identifier, and at least one optical reading device is provided and arranged to detect the displayed optically readable identifier. The manipulator system is arranged to release control of the manipulator by means of the mobile operating device when the optically readable identifier has been correctly detected by the optical reading device.

Abstract: In one example embodiment, a robotic vacuum sorting system comprises: a suction gripper mechanism mounted to a sorting robot; a vacuum system coupled to the suction gripper mechanism; robot control logic and electronics coupled to the sorting robot and the vacuum system; and an imaging device coupled to the robot control logic and electronics. In response to an image signal from the imaging device, the robot control logic and electronics outputs robot control signals to control the sorting robot, and outputs one or more airflow control signals to the vacuum system to execute a capture action on a target object using the suction gripper. During the capture action, the robot control logic and electronics outputs control signals such that the vacuum system pulls a vacuum at the gripping port of the suction gripper mechanism as the suction gripper mechanism is applied to capture and hold the target object.

Abstract: Techniques are described for automating aspects of the property condition monitoring process to efficiently determine a present property condition, and perform various actions associated with the determined property condition. In some implementations, a first set of image data for a region of the property is obtained prior to a start of the rental period. A determination that the rental period has ended at the property is made. A second set of image data for the region of the property is obtained in response to the determination. A representation of a difference between the first set of image data and the second set of image data is determined. An indication of the representation of the difference between the first set of image data and the second set of image data is provided for output to a computing device of a user associated with the property.

Abstract: A robot includes a controller configured to: detect a virtual wall signal; identify a virtual wall according to a signal threshold and the virtual wall signal; and when the virtual wall is identified, adjust the signal threshold, and control the robot to travel along an outer side of the virtual wall according to an adjusted signal threshold and the virtual wall signal, such that a driving wheel of the robot is located at the outer side of the virtual wall when the robot is traveling along the outer side of the virtual wall; wherein the outer side of the virtual wall is a side of the virtual wall within an active region of the robot.

Abstract: A method of analyzing seeds including acquiring, using an X-ray machine, X-ray images of the seeds. Analyzing the X-ray images to determine a parameter of each of the seeds. Comparing a parameter determined from analyzing the X-ray image of one seed to a parameter determined from analyzing the X-ray image of another seed. Arranging the seeds relative to each other based on the seed parameters.

Abstract: In various embodiments, an electronic device includes one or more sensors, a driving module comprising driving circuitry configured to move the electronic device, a memory, and a processor. The processor may be configured to execute instructions to control the electronic device to determine a first distance between the electronic device and a user using at least one of the one or more sensors, and to acquire information corresponding to a gesture of the user through at least one of the one or more sensors based on the first distance being within a first predefined range. The processor may be further configured to control the electronic device to move using the driving module, based on the first distance being within a second predefined range, such that the electronic device is located within the first predefined range and acquires the information corresponding to the gesture of the user through at least one of the one or more sensors.

Abstract: Certain aspects relate to systems and techniques for medical robotic systems that leverage a versatile, open kinematic chain together with a set of medical-procedure-specific software-controlled actuation constraints in order to perform a variety of medical procedures. The robotic system can be operated in a first mode by identifying a remote center and constraining the actuation of motorized joints to maintain intersection of at least an insertion axis with the remote center. The robotic system can be operated in a second mode by identifying a virtual rail position and constraining the actuation of motorized joints to maintain alignment of the insertion axis along the virtual rail.

Abstract: A point cloud information acquiring unit for acquiring point cloud information of a region including at least one of the picking hand and the work at a time which is at least one of (i) when the picking hand picks the work at the first position, (ii) when the picking hand moves the work out of the first container, (iii) when the picking hand moves the work in the second container and (iv) when the picking hand arranges the work at the second position; and an abnormality detection unit for detecting an abnormality based on the point cloud information acquired by the point cloud information acquiring unit are included.

Abstract: Camera control and image streaming are described, including at least one camera or an apparatus associated with at least one camera. The camera or apparatus is configured to establish a first communication with a first device, where the first communication allows the first device to control the camera, including one or more of zooming the camera, panning the camera, and tilting the camera. The camera or apparatus is configured to establish a second communication with a second device, where the second communication allows the second device to control the camera, including one or more of zooming the camera, panning the camera and, tilting the camera. The first communication and/or the second communication may include streaming a view from the camera to a device or user. The camera may be carried by an unmanned flying object.

Abstract: A robot comprising: a base; a flexible arm extending from the base having: a plurality of joints positioned throughout the arm, a plurality of drivers arranged to drive the joints, and an attachment structure for attaching a tool to the arm; and a control unit configured to control the drivers and to receive inputs from sensors, where the control unit (i) controls the drivers to permit the arm to be reconfigured by the action of an external force applied to the arm to cause the tool to be retracted from a port; and (ii) on receiving sensor input indicating that the arm has been reconfigured to cause the tool to be retracted from the port, controls the drivers to reconfigure the arm so as to agitate the tool transverse to a longitudinal axis of the tool.

Abstract: A trajectory information generating unit is included, the trajectory information generating unit generating trajectory information that defines a trajectory for which a picking hand picks one of one or more works stored in one supply container included in one or more supply containers and arranges the work in one arrangement container included in one or more arrangement containers. After performing a process of generating trajectory information representing a first work included in the one or more works and before a movement of the first work is completed, the trajectory information generating unit may generate trajectory information representing a second work included in the one or more work and different from the first work by using an operation result in the process of generating the trajectory information regarding the first work.

Abstract: A robotic system includes: a control unit configured to: receive an object set including one or more object entries, wherein: the object entries correspond to source objects of an object source, each of the object entries are described by one or more object entry properties; receive sensor information representing one or more detectable object properties for detectable source objects of the object source; calculate an object match probability between the detectable source objects and the object entries based on a property correlation between the detectable object properties of the detectable source objects and the object entry properties of the object entries; generate an object identity approximation for each of the detectable source objects based on a comparison between the object match probability for each of the detectable source objects corresponding to a particular instance of the object entries; select a target object from the detectable source objects; generate an object handling strategy, for impleme

Abstract: The objective of the present invention is to provide an autonomous localization and navigation equipment which has the following advantages. The autonomous localization and navigation equipment is highly modularized, which greatly reduces the coupling degree with the host equipment, so the equipment is convenient to be integrated to the existing host equipment and it is flexibly expandable. Thus, the host equipment such as a robot etc. has a more concise and clear system constitution, thereby greatly reducing the development difficulty and developing time of the host equipment having the autonomous localization and navigation equipment 1. Moreover, as a result of the high degree of modularization of the autonomous localization and navigation equipment, it is possible to miniaturize the host equipment.

Abstract: An electro-mechanical device cuts plant stems at a desired angle after a stem is inserted into a stem shaft and a sensor triggers activation of a blade along a blade path at a desired angle. A portable device powered by batteries can be used with plantings where they are growing or a powered device can be used for line production or high volume work.

Abstract: A computer-implemented method executed by a robotic system for performing a positional search process in an assembly task is presented. The method includes applying forces to a first component to be inserted into a second component, detecting the forces applied to the first component by employing a plurality of force sensors attached to a robotic arm of the robotic system, extracting training samples corresponding to the forces applied to the first component, normalizing time-series data for each of the training samples by applying a variable transformation about a right tilt direction, creating a time-series prediction model of transformed training data, applying the variable transformation with different directions for a test sample, and calculating a matching ratio between the created time-series prediction model and the transformed test sample.

Abstract: The present disclosure relates to a method of identifying an unexpected obstacle and a robot implementing the method. The method includes: by a sensing module of a robot, sensing a blind spot located in a traveling path of the robot; by a control unit of the robot, calculating a probability that a moving object appears in the sensed blind spot; and, by the control unit, controlling the speed or direction of a moving unit of the robot based on the calculated probability.

Abstract: The present invention relates to a moving robot capable of recognizing a position on a map and a control method of the moving robot, and the moving robot according to the present invention includes: a travel drive unit configured to move a main body; an image acquisition unit configured to acquire images of surroundings; and a controller configured to recognize a current position.

Abstract: A method for calibrating a system with a conveying apparatus and at least a first robot includes determining the positions of at least three measuring points of a first component transported by the conveying apparatus in a first transport position using the first robot. The method further includes determining the position of at least one of the measuring points in a second transport position using the first robot, or determining the positions of at least two of the measuring points of the component in a third transport position and the position of at least one other measuring point in the third transport position or at least one of these measuring points in a fourth transport position using at least one second robot.

Abstract: An image processing system, an image processing device and an image processing method that can improve performance of an image measurement are provided. A control device controls a light emission portion in a manner that each of plural types of partial regions set on a light emission surface emits light, and controls a camera to image an object in synchronization with light emission of each of the plural types of partial regions. The control device performs an image measurement of the object based on reflection profile information which is generated based on a plurality of input images, and the reflection profile information shows a relationship between positions within the light emission surface and degrees of light reflected at attention sites of the object and incident to the camera with respect to light irradiated from the position to the object.

Abstract: A door opening and closing robot includes: a door operating tool including an insertion and restricting portion; a robotic arm that moves the door operating tool; and a control device that: operates the robotic arm, wherein the door operating tool moves to a first reference position, then moves toward a first presence confirmation position; obtains a position of the door operating tool as a first evaluation position; and determines a deviation between the first presence confirmation position and the first evaluation position, when the deviation is less than or equal to a predetermined first threshold, detects failed presence of the insertion portion in a window groove. The first reference position is the operating tool which is inserted in the window groove and the restricting portion is in contact with an edge of the window groove or positioned above the edge of the window groove.

Abstract: A cable damage detection assistance apparatus in a robot mechanism includes a program executor for executing a program to operate a robot, a plurality of times, while changing velocity for driving motors whenever the program is executed; a motor controller for controlling the motors; a state quantity detector for detecting a state quantity indicating an operation state of the robot during the execution of the program; an alarm generator that, when the state quantity exceeds a threshold value, generates an alarm and outputs information about a line number at that time; an alarm database for counting the number of occurrence of alarms on each line number on which the alarm has occurred, and storing the alarm occurrence number on each line number on a velocity-by-velocity basis; and an analysis display for displaying the relationship between the alarm occurrence number and the velocity on each line number.

Abstract: Disclosed is a robot projecting an image that selects a projection area in a space based on at least one of first information related to content of an image to be projected and second information related to a user viewing the image to be projected, and projects the image to the projection area.

Abstract: A method of planning a cleaning route for a cleaning robot: firstly, starting from an original point based on maps of grids, cleaning grid zones formed by the grids one by one until an entire region is cleaned, and then establishing a map of the entire region; secondly, searching the map of the entire region to find out uncleaned areas missed from cleaning, and then cleaning the uncleaned areas; thirdly, cleaning peripheral areas of the entire region based on the map of the entire region; and lastly, returning to the original point. A chip is also provided which stores procedures for controlling the cleaning robot to implement the method of planning a cleaning route.

Abstract: A method for operating a cleaning device that automatically moves within an environment, wherein the cleaning device cleans a surface according to a prescribed work plan, wherein a detection device of the cleaning device detects contamination levels of several partial surface areas of the surface, wherein a cleaning operation of the cleaning device is varied as a function of the detection result, wherein an overall contamination level is determined for the surface from the contamination levels of several partial surface areas, and the cleaning operation is performed with cleaning parameters identical to the overall contamination level for the entire surface. In order to create an alternative to conventional operating methods, the determined overall contamination level is compared with at least one reference contamination level, specifically with an overall contamination level determined during a chronologically preceding cleaning activity.

Abstract: Provided is a machine learning device configured to perform machine learning related to optimization of a compensation value of a compensation generation unit with respect to a servo control device configured to control a servo motor configured to drive an axis of a machine tool, a robot, or an industrial machine, and that includes at least one feedback loop, a compensation generation unit configured to generate a compensation value to be applied to the feedback loop, and an abnormality detection unit configured to detect an abnormal operation of the servo motor, wherein, during a machine learning operation, when the abnormality detection unit detects an abnormality, the compensation from the compensation generation unit is stopped and the machine learning device continues optimization of the compensation value generated by the compensation generation unit.

Abstract: Concerning a partial area image that constitutes a wide area image, to measure an elapsed time from a past point of time of image capturing and control a flying body in accordance with the elapsed time, an information processing apparatus includes a wide area image generator that extracts, from a flying body video obtained when a flying body captures a ground area spreading below while moving, a plurality of video frame images and combines the video frame images, thereby generating a captured image in a wide area, an elapsed time measurer that measures an elapsed time from an image capturing time by the flying body for each of the plurality of video frame images, and an output unit that outputs the elapsed time for each video frame image together with position information of the flying body at the time of capturing of the video frame image.

Abstract: The present disclosure discloses a robot cleaner, including a cleaner body; and a sensing unit disposed in the cleaner body, wherein the sensing unit includes a rotating body configured to be horizontally rotatable around a rotation shaft passing through an inside of the cleaner body; a sensing unit mounted on one side of the rotating body to sense a feature or an obstacle in the vicinity of the cleaner body; and a tilting unit installed inside the rotating body to vertically tilt the sensing unit.

Abstract: An apparatus for notifying of parcel delivery comprising an aerial parcel delivery apparatus, landing gear, a processor, a number of visual sensors, and an articulated robotic arm. The robotic arm may comprise an end effector comprising one or more simulated fingers or digits of a human hand, a protruding member, and a wireless communication adapter. The end effector may have the ability to grasp an object or actuate a doorbell, key pay, or an alarm system. The articulated robotic arm including a protruding member is extended to ring a doorbell.

Abstract: A system and method of determining a grasp type of an end-effector of a robot when interacting with an item wherein a plurality of velocity values of the end-effector at various positions of its movement are collected and used to determine the grasp type when a given velocity value is below a predetermined threshold.

Abstract: A method for AI-assisted service provisioning and modification for delivering message-based services, including: receiving an input sequence from a user in relation to a request for a service, the input sequence including one or more inputs; processing the input sequence to determine a service type; associating a workflow with the request based at least in part on the service type and a profile of the user, the workflow including a set of one or more steps, a step of the set of one or more steps corresponding to a set of attributes including at least one of: a communication mode, a communication type, or a communication priority, the workflow being performed by at least one of: a chatbot, an AI assistant, or a service professional; and interacting with the user based at least in part on the workflow to deliver the service.

Abstract: An industrial robot having high operability for a user is provided. An industrial robot includes a manipulator, a controller which controls an operation of the manipulator, and a detection device attached to the manipulator and detecting a gesture input. The controller executes a process corresponding to the detected gesture input.

Abstract: An image processing system (SYS) specifies an arrangement situation of a workpiece (W) provided by a line (L). The image processing system (SYS) specifies a normal (V) with respect to a set measurement point (Wp) of the workpiece (W) according to the specified arrangement situation of the workpiece (W), and changes a position and posture of the two-dimensional camera (310) so that the specified normal (V) matches an optical axis of the two-dimensional camera (310) (S1). The image processing system (SYS) changes a distance between the two-dimensional camera (310) and the measurement point (Wp) so that the specified normal (V) matches the optical axis of the two-dimensional camera (310), to focus the two-dimensional camera (310) on the measurement point (Wp).

Abstract: A method for controlling a velocity of a conveyance path of a system including an industrial robot, a first conveyance path configured to transfer items within a working area (b2) of the robot with a velocity v1, and a second conveyance path configured to transfer empty places within the working area (b2) of the robot with a velocity v2. The method includes: obtaining position data for a plurality of items and for a plurality of empty places; creating one or more pairs including one of the empty places of the plurality of empty places and a respective item of the plurality of items; calculating, for one of the one or more pairs, a time tAs for the empty place of the one pair and a time tBk for the item of the one pair to reach a border of the working area (b2) based on position data for the one pair and the velocities v1 and v2; and controlling the velocity v2 of the second conveyance path based on a difference between the time tAs and a time (tBk+?t), where ?t is a predetermined time difference.

Abstract: A docking system and method for charging a mobile robot at a docking station. The system includes a first module for the robot, including a first communication unit and a first control unit, and a second module for the station, including a second communication unit, one or more docking sensors, and a second control unit. When the robot enters a docking region around the station, the first communication unit sends to the second communication unit a status message indicating that the robot needs charging; upon reception of the status message, the second control unit uses the sensors to derive a traction command to drive the robot towards the station; and the second communication unit sends to the first communication unit a command message containing the traction command. The first control unit processes the traction command and uses it to operate traction motors of the robot.

Abstract: The invention provides a probe device, a precision detection method, a precision detection system, and a positioning system. The probe device includes a positioning part and a guide detection part, wherein the positioning part is provided with a support having three or more non-collinear positioning element installed thereon, and the guide detection part is connected with the support, has a first preset positional relation with the positioning elements, and has a cylindrical outer contour matched with a guide element of the positioning system. The precision of the guide element can be accurately detected, so that the control precision of a surgical robot is effectively improved, and the system safety is improved.

Abstract: Features are disclosed for an end effector for automated identification and handling of an object. The end effector includes an end effector that can be positioned over a pick point of an overpackage in which a desired object is location using sensors. Using the location information, the end effector can identify a path to the pick point and detect whether the pick point is engaged by detecting environmental changes at the end effector.

Abstract: A method for repairing a bone of a patient may include superimposing a first virtual boundary on a virtual bone and superimposing a second virtual boundary on the virtual bone. The method may further include robotically modifying the bone of the patient with a planar tool along a first working boundary to create a first surface. The first working boundary may correspond to the first virtual boundary. The method may further include robotically modifying the bone of the patient with a rotary tool along a second working boundary to create a second surface. The second working boundary may correspond to the second virtual boundary.

Abstract: The present disclosure relates to an information processing device and an information processing method that are capable of estimating the self-position by accurately and continuously estimating the self-movement. The information processing device according to an aspect of the present disclosure includes a downward imaging section and a movement estimation section. The downward imaging section is disposed on the bottom of a moving object traveling on a road surface and captures an image of the road surface. The movement estimation section estimates the movement of the moving object in accordance with a plurality of images representing the road surface and captured at different time points by the downward imaging section. The present disclosure can be applied, for example, to a position sensor mounted in an automobile.

Abstract: Techniques for localizing a device based on images captured by the device. The techniques include receiving, from a device via a data communication network, image frame data for frames captured by an imaging camera included in the device, the frames including a first frame, automatically detecting real-world objects captured in the image frame data, automatically classifying the detected real-world objects as being associated with respective object classes, automatically identifying object class and instance dependent keypoints for the real-world objects based on the object classes associated with the real-world objects, and estimating a pose of the device for the first frame based on at least the identified object class and instance dependent keypoints.

Abstract: A machine learning device that learns an operation of a robot for picking up, by a hand unit, any of a plurality of workpieces placed in a random fashion, including a bulk-loaded state, includes a state variable observation unit that observes a state variable representing a state of the robot, including data output from a three-dimensional measuring device that obtains a three-dimensional map for each workpiece, an operation result obtaining unit that obtains a result of a picking operation of the robot for picking up the workpiece by the hand unit, and a learning unit that learns a manipulated variable including command data for commanding the robot to perform the picking operation of the workpiece, in association with the state variable of the robot and the result of the picking operation, upon receiving output from the state variable observation unit and output from the operation result obtaining unit.

Abstract: Methods, systems, and apparatus, including computer programs encoded on storage devices, for monitoring, security, and surveillance of a property. In one aspect, a system includes multiple robotic devices, multiple sensors, wherein the multiple sensors includes a first sensor, multiple charging stations, and a monitor control unit. The monitor control unit may include a network interface, one or more processors, and one or more storage devices that include instructions to cause the one or more processors to perform operations. The operations may include receiving data from the first sensor that is indicative of an alarm event, accessing information describing the capabilities of the each of the robotic devices, selecting a subset of robotic devices from the multiple robotic devices, and transmitting a command to each robotic device in the subset of robotic devices that instructs each respective robotic device to deploy to the location of the first sensor.

Abstract: A mobile robot includes a mode of operation to recover from a localization error. The mobile robot detects a change in state in a local region proximate the mobile robot. The location of the mobile robot is identified based at least in part on the detected change in state. In one implementation, the mobile robot interfaces with a system controller of a building to initiate a change in state in a local region of a building.

Abstract: This disclosure relates to methods, non-transitory computer readable media, and systems that use a local-lighting-estimation-neural network to estimate lighting parameters for specific positions within a digital scene for augmented reality. For example, based on a request to render a virtual object in a digital scene, a system uses a local-lighting-estimation-neural network to generate location-specific-lighting parameters for a designated position within the digital scene. In certain implementations, the system also renders a modified digital scene comprising the virtual object at the designated position according to the parameters. In some embodiments, the system generates such location-specific-lighting parameters to spatially vary and adapt lighting conditions for different positions within a digital scene.

Abstract: The present disclosure relates to using an object relighting neural network to generate digital images portraying objects under target lighting directions based on sets of digital images portraying the objects under other lighting directions. For example, in one or more embodiments, the disclosed systems provide a sparse set of input digital images and a target lighting direction to an object relighting neural network. The disclosed systems then utilize the object relighting neural network to generate a target digital image that portrays the object illuminated by the target lighting direction. Using a plurality of target digital images, each portraying a different target lighting direction, the disclosed systems can also generate a modified digital image portraying the object illuminated by a target lighting configuration that comprises a combination of the different target lighting directions.

Abstract: In some implementations, techniques are described for generating and displaying visualizations that display information for an electronic device in a visual interface presented to a user by an augmented reality (AR) device. Video data collected by an augmented reality device is obtained. A device of a property is identified based on the video data. In response to identifying the device, a network status for the device is obtained. One or more visualizations representing the network status for the device are generated. The one or more visualizations are provided for display to a user by the augmented reality device.

Abstract: An interactive play device, method and apparatus, is disclosed that includes means for generating a plurality of interactions, input control mechanisms, means for storing responses to interactions, and control means to select the next interaction based on memorized responses. This invention provides a new class of interactive play devices, which is founded on personalizing a play device so that its current functionality is based on how the player has interacted with it in prior playing sessions. The invention also discloses a doll device and a car device, which operate in a plurality of states that mimic human behavior. Further, the specification describes a game during which the player is challenged to transform a play device from an initial state to a desired state by providing appropriate responses to interactions initiated by the device.