Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium that distributes skill bundles that can guide robot execution. One of the methods includes receiving data for a skill bundle from a skill developer. The data can include a definition of one or more preconditions for a robotic system to execute a skill; one or more effects to an operating environment after the robotic system has executed the skill; and a software module implementing the skill. The software module can define a state machine of subtasks. A skill bundle can be generated from the data received from the skill developer. Data identifying the generated skill bundle can be added to a skill registry. The skill bundle can be provided to the execution robot system for installation on the robot execution system.

Abstract: A computer-implemented method for controlling a robot, the method comprising: determining a first value for a first joint parameter associated with a first continuum joint included in the robot and a first value for a second joint parameter associated with the first continuum joint, wherein the first joint parameter indicates a bending radius of a flexible portion of the continuum joint, and the second joint parameter indicates a rotation of the flexible portion of the continuum joint with respect to a base portion of the first continuum joint; and positioning an end portion of the robot at a final target location based on the first value of the first joint parameter and the first value of the second joint parameter.

Abstract: According to the present invention, a moving body capable of moving within a preset range of movement acquires an image from the environment surrounding the location of the moving body, and determines entry determination conditions for obtaining a result of an entry determination as to whether or not the moving body is allowed to enter a region identified by the location of the moving body and the image. A management terminal outputs the entry determination conditions and the image to an output device, and receives modification information relating to the entry determination conditions from an input device. A server uses the modification information received by the input device of the management terminal to perform learning, including updating of the entry determination conditions, thereby setting the movement range of the moving body, the movement of which is controlled in accordance with the entry determination result.

Abstract: The present invention relates to methods for learning a robot task and robots systems using the same. A robot system may include a robot configured to perform a task, and detect force information related to the task, a haptic controller configured to be manipulatable for teaching the robot, the haptic controller configured to output a haptic feedback based on the force information while teaching of the task to the robot is performed, a sensor configured to sense first information related to a task environment of the robot and second information related to a driving state of the robot, while the teaching is performed by the haptic controller for outputting the haptic feedback, and a computer configured to learn a motion of the robot related to the task, by using the first information and the second information, such that the robot autonomously performs the task.

Abstract: The present invention relates to a robot and a control method therefor and, more particularly, to a robot and a control method therefor, the robot detecting peripheral obstacles and structures by using an image in front of same, thereby providing an efficient and safe moving path. A robot control method according to one embodiment of the present invention comprises the steps of: capturing an image; acquiring a first image of which the bottom surface is separated in the image; recognizing obstacles included in the image by using a learned first artificial intelligence model; allowing a robot to acquire and store a second image in order to perform a task on the basis of the information about the first image and the region including the recognized obstacles; and allowing the robot to move on the basis of the second image.

Abstract: An apparatus for automated collision avoidance includes a sensor configured to detect an object of interest, predicting a representation of the object of interest at a future point in time, calculating an indication of a possibility of a collision with the object of interest based on the representation of the object of interest at the future point in time, and executing a collision avoidance action based on the indication.

Abstract: A robot control device includes: a learned model created through learning work data composed of input and output data, the input data including states of a robot and the surroundings where humans operate the robot to perform a series of works, the output data including human operation corresponding to the case or movement of the robot caused thereby; a control data acquisition section that acquires control data by obtaining output data related to human operation or movement from the model, being presumed in response to and in accordance with the input data; a completion rate acquisition section acquiring a completion rate indicating to which progress level in the series of works the output data corresponds; and a certainty factor acquisition section that acquires a certainty factor indicating a probability of the presumption in a case where the model outputs the output data in response to the input data.

Abstract: A control device includes a motion controller configured to control operation of a mechanical apparatus according to an operational command, a correction controller configured to correct the operation of the mechanical apparatus according to manipulational information outputted from a manipulating device, a memory part configured to store first operational information indicative of the operation of the mechanical apparatus, and correctional information indicative of the correction made by the correction controller, and a learning part configured to carry out machine learning using the first operational information and the correctional information corresponding to the first operational information. The motion controller controls the operation of the mechanical apparatus according to the operational command based on the command of the learning part, and the manipulating device outputs the manipulational information based on second operational information indicative of motion of the manipulating device.

Abstract: The present application provides a kinematics modeling method, apparatus and device for a multi-degree-of-freedom mechanism and a storage medium. The method includes: constructing a point coordinate system, and constructing the transformation matrix; constructing transformation matrices of two rotating axes and the transformation matrix; constructing the forward kinematics model based on the transformation matrices of the point coordinate system, the two rotating axes and the workpiece coordinate system; solving the motor value of the rotating axis through the rotation matrix of the end-effector, using the translation matrix of the end-effector as a non-homogeneous linear equation set, solving the motor value of linear axis.

Abstract: The motion detecting device that detects motion of an operator's finger for remotely operating a multi-articulated robot includes a device main body that is installed such that the finger is placed thereon, a contact part that follows a shape of the finger in the device main body and is in contact with the finger, and a detection part that detects the motion of the finger on the basis of a pressing state of the finger against the contact part.

Abstract: A robotic singulation system is disclosed. In various embodiments, sensor data image data associated with a plurality of items present in a workspace is received. The sensor data is used to determine and implement a plan to autonomously operate a robotic structure to pick one or more items from the workspace and place each item singly in a corresponding location in a singulation conveyance structure. The plan includes performing an active measure to change or adapt to a detected state or condition associated with one or more items in the workspace.

Abstract: An advertising method for a shuttle comprises by a controller, responsive to identifying a drop-off location and a business paying to influence a route traveled by the shuttle, selecting one of a plurality of routes to the drop-off location according to a priming estimate indicating that points of interest along the one share more characteristics with the business relative to others of the plurality; and commanding the shuttle to travel the one.

Abstract: A remote robot system and a method of controlling a remote robot system capable of responding appropriately according to a user are provided. A remote robot system includes: a robot configured to perform a predetermined operation including collection of local information near the robot; a guide terminal capable of remotely operating the operation of the robot; and a participant terminal capable of remotely communicating with the guide terminal, in which the participant terminal includes: a display panel configured to output the local information acquired from the robot to the user; and an interest detection unit configured to detect user's interest in the output local information.

Abstract: A method includes inputting a source into a weighted and undirected graph having a plurality of nodes and edges, inputting a target, inputting a plurality of objectives, searching the graph using a rapidly exploring random tree algorithm to determine a solution path that meets an existence constraint and an order constraint, determining a plurality of paths between the source and the target that intersects with each one of the plurality of objectives at least once that conforms with the existence constraint, assigning a travel cost for each of the determined plurality of paths, determining a visiting order of the plurality of objectives that reduces the assigned travel cost by the RRT* algorithm asymptotically decreasing with an allocated computation time by rewiring each one of the plurality of objectives and outputting the solution path to form a connected graph having the plurality of nodes.

Abstract: A path generation device including an acquisition unit, a setting unit, and a path generation unit. The acquisition unit is configured to acquire pose information relating to an initial pose and a target pose of a robot, position information relating to a position of the robot, obstacle information including a position of an obstacle present in a range of interference with the robot, and specification information relating to a specification including a shape of the robot. The setting unit is configured to, based on a positional relationship between the robot and the obstacle, set a clearance amount representing an amount of clearance to avoid the interference for at least one out of the robot or an obstacle present in a range of interference with the robot.

Abstract: A control method for a robot includes: determining a desired zero moment point (ZMP) of the robot; obtaining a position of a left foot and a position of a right foot of the robot, and calculating desired support forces of the left foot and the right foot according to the desired ZMP, the positions of the left foot and the right foot; obtaining measured support forces of the left foot and the right foot, and calculating an amount of change in length of the left leg and an amount of change in length of the right leg according to the desired support forces of the left foot and the right foot, the measured support forces of the left foot and the right foot; and controlling the robot to walk according to the amount of change in length of the left leg and the right leg.

Abstract: A robot control method includes: determining a planned capture point and a measured capture point of the robot so as to calculate a capture point error of the robot; obtaining positions of a left foot and a right foot of the robot, and a planned zero moment point (ZMP) of the robot so as to calculate desired support forces of the left foot and the right foot; calculating desired torques of the left foot and the right foot according to the capture point error, the desired support forces of the left foot and the right foot; obtaining measured torques of the left foot and the right foot so as to calculate desired poses of the left foot and the right foot; and controlling the robot to walk according to the desired poses of the left foot and the desired pose of the right foot.

Abstract: A method for detecting an erroneous velocity data using a controller in communication with a velocity sensor onboard a vehicle includes receiving a time-series velocity data from the velocity sensor, calculating a time-series acceleration data using the time-series velocity data, calculating a time-series jerk data using the time-series acceleration data, calculating a saturated (numerically bounded) jerk data using the time-series jerk data, calculating an estimated acceleration data using the saturated jerk data, calculating a difference between the estimated acceleration data and the time-series acceleration data, and determining whether the difference is greater than a threshold value. The erroneous velocity data is detected in response to the difference being greater than the threshold value.

Abstract: This application provides a method for controlling a robot cleaner, a robot cleaner, and a storage medium. The method for controlling the robot cleaner includes the steps of: acquiring a weight of the water tank, comparing the weight of the water tank with a setting value to acquire a comparison result, determining a remaining usable time of the robot cleaner according to the comparison result, and controlling the robot cleaner according to the remaining usable time. Since the weight of the water tank is not easily interfered by other factors, the acquiring of weight has a high accuracy, thereby the remaining usable time determined according to the weight of the water tank has a high accuracy, and then the robot cleaner is controlled according to the remaining usable time with higher accuracy. The control accuracy of the robot cleaner thus can be improved.

Abstract: Disclosed herein are apparatus and method for resisting external articulation of one or more joints of a manipulator assembly when the joints are approaching mechanical limits. For example, an articulable system may include a joint mechanism, an actuator coupled to the joint mechanism, a sensor system for sensing a joint state and a controller. The controller can operate the articulable system in an external articulation facilitation mode. The controller can command the actuator to resist movement of the joint in response to the joint state indicating the joint is moving toward a mechanical limit location with a joint velocity meeting a first velocity criterion. The controller can also command the actuator resist movement of the joint at a second joint position when the joint velocity meets a second criterion.