Abstract: It is possible to perform robot motor learning in a quick and stable manner using a reinforcement learning apparatus including: a first-type environment parameter obtaining unit that obtains a value of one or more first-type environment parameters; a control parameter value calculation unit that calculates a value of one or more control parameters maximizing a reward by using the value of the one or more first-type environment parameters; a control parameter value output unit that outputs the value of the one or more control parameters to the control object; a second-type environment parameter obtaining unit that obtains a value of one or more second-type environment parameters; a virtual external force calculation unit that calculates the virtual external force by using the value of the one or more second-type environment parameters; and a virtual external force output unit that outputs the virtual external force to the control object.

Abstract: The present invention is directed to the use and application of robotics in mining and post-mining applications, including smelting and processes associated with electrodeposition, electrorefining, cleaning, and disposal. In addition, the application of robotics includes functions associated with maintenance and operation of equipment used in mining operations.

Abstract: A bipedal robot having a pair of legs with 6 degrees of freedom and a control method thereof which calculate a capture point by combining the position and velocity of the center of gravity (COG) and control the capture point during walking to stably control walking of the robot. A Finite State Machine (FSM) is configured to execute a motion similar to walking of a human, and thus the robot naturally walks without constraint that the knees be bent all the time, thereby being capable of walking with a large stride and effectively using energy required while walking.

Abstract: A robot displacement device for use with a robotic frame shaped to approximate and be coupleable to at least a portion of the human body and configured to mimic movement of the human body. The device employs a plurality of force sensors which are attached to the robotic frame which detect a baseline controlling interface force status relationship between the sensors and the extremities of the human operator. Based on the output force signal from the sensors and the force and direction of gravity relative to the robotic frame, the computation system calculates at least a rotational force required to maintain the controlling force status relationship. That system then generates and transmits an actuation signal to a drive system attached to the robotic frame which displaces a portion of the robotic frame in order to maintain the controlling force status relationship.

Abstract: A method according to the invention for controlling a manipulator, in particular a robot, includes the following steps: determining (S10, S20) a target path (q(s)) of the manipulator, and determining (S70) a motion value (v(s)) for this target path, optionally, determining (S50) a path segment ([s_A, s_E]) with a defined profile of a motion value (v(s)=vc), and automatically determining (S60) this motion value on the basis of motion values (v_max_RB, v_max_vg) permissible in this path segment.

Abstract: A medical robotic system includes an entry guide with articulatable instruments extending out of its distal end, an entry guide manipulator providing controllable four degrees-of-freedom movement of the entry guide relative to a remote center, and a controller configured to manage operation of the entry guide manipulator in response to operator manipulation of one or more input devices. As the entry guide manipulator approaches a yaw/roll singularity, the controller modifies its operation to allow continued movement of the entry guide manipulator without commanding excessive joint velocities while maintaining proper orientation of the entry guide.

Abstract: A program changing device includes a sequence interchanging unit for interchanging plural teaching points in a teaching sequence such that total movement time of a robot becomes smaller than that when the robot is moved in line with an initial teaching sequence of the teaching points, a calculating unit for calculating difference amounts between the initial teaching points and a trajectory of the robot that is obtained by executing an after-interchanged operational program by simulation, a position adjusting unit for adjusting positions of the teaching points of the after-interchanged operational program until the difference amounts become equal to or smaller than a predetermined allowable value, and a teaching point changing unit for changing the adjusted teaching points to be the initial teaching points when cycle time of the after-interchanged operational program including the adjusted teaching points is longer than initial cycle time.

Abstract: The invention relates to a medical robot (R) and a method for meeting the performance requirements of a medical robot (R). The robot (R) comprises several axes (1-6) and a controller (17). A medical tool (21-24) is fixed to a fixing device (18) on the robot (R) and the working range (30) of the robot (R) is set by the controller (17) in particular with safe techniques such that the robot (R) meets the performance requirements of the medical tool (21-24).

Abstract: A controller determines a set of solutions to an inverse kinematic relationship relating received three axes position and orientation requirements defining a tool control point (TCP) of a robotic manipulator, the robotic manipulator comprising at least seven revolute joints, to a respective angular position of each of the seven revolute joints. The set of solutions specifies, in terms of an angular position of a first revolute joint proximate to a proximal end of the robotic manipulator, at least one set of angular positions of the second, third, fourth, fifth, sixth and seventh revolute joints. The set of solutions results from solving only closed-form mathematical expressions.

Abstract: A master-slave manipulator includes a remote manipulation device, a slave manipulator, and a control unit. The remote manipulation device as a master gives an operating command corresponding to a plurality of degrees of freedom. The slave manipulator includes a plurality of joints corresponding to the degrees of freedom. The slave manipulator includes a redundant joint among the joints. The control unit controls operations of the joints in accordance with the operating command. The control unit calculates an orientation change of the remote manipulation device from the operating command at predetermined time intervals and selects and drives one of the joints in redundancy relationship among the joints in accordance with the orientation change.

Abstract: There is provided a robot apparatus that can rapidly obtain an ellipse indicating a stiffness characteristic, even if lengths of two links are different from each other.

Abstract: Methods and apparatus for procedural memory learning to control a robot by demonstrating a task action to the robot and having the robot learn the action according to a similarity matrix of correlated values, attributes, and parameters obtained from the robot as the robot performs the demonstrated action. Learning is done by an artificial neural network associated with the robot controller, so that the robot learns to perform the task associated with the similarity matrix. Extended similarity matrices can contain integrated and differentiated values of variables. Procedural memory learning reduces overhead in instructing robots to perform tasks. Continued learning improves performance and provides automatic compensation for changes in robot condition and environmental factors.

Abstract: A Real Time Locating System (RTLS) hygiene management and monitoring system for individuals and companies to manage and monitor the hygiene of their surroundings. In some embodiments of the invention, RTLS is used to monitor and manage cleanliness of rooms and surfaces and the location of cleaning supplies and cleaning personnel. The invention provides improved efficiency and quality of hygiene services. For instance, the invention can enable prioritization of cleaning, improve efficient use of cleaning supplies and cleaning personnel, track short and long term cleaning operations, and provide insight into ineffective cleaning.

Abstract: Improvements are disclosed for a load-clamping system with variable clamping force control by which a wide variety of dissimilar loads of different types, geometric configurations and/or other parameters can be accurately clamped at respective variable optimal clamping force settings. An operator terminal cooperates with a controller to translate one or more possible load parameters into a form easily discernible visually by a clamp operator and preferably easily comparable by the clamp operator, from his visual observation, to each particular load which he is about to engage, so that the clamp operator can interactively guide the controller in its selection of an optimal clamping force setting for each particular load.

Abstract: A trajectory planning system obtains a trajectory for controlling a state of an object toward a goal state. The system includes a search tree generating section which registers a state of the object as a root of a search tree in a state space, registers a next state of the object after a lapse of a predetermined time interval obtained through dynamical relationships during the time interval as a branch of the search tree in the state space.

Abstract: A medical robotic system includes an entry guide with articulatable instruments extending out of its distal end, an entry guide manipulator providing controllable four degrees-of-freedom movement of the entry guide relative to a remote center, and a controller configured to manage operation of the entry guide manipulator in response to operator manipulation of one or more input devices. As the entry guide manipulator approaches a yaw/roll singularity, the controller modifies its operation to allow continued movement of the entry guide manipulator without commanding excessive joint velocities while maintaining proper orientation of the entry guide.

Abstract: A method for controlling behavior of an intelligent mechanical system having more than one degree of freedom. The method includes (a) providing a target to a selector unit that requires operation of actuators of the mechanical system; (b) generating by a selector unit more than one behavior commands adapted to reach the target; (c) simulating movements of the mechanical system for each behavior command by a computing unit of the mechanical system; (d) assessing fitness values for each simulated movements based on at least one objective; and (e) sending the behavior commands with a highest fitness value to the actuators of the mechanical system.

Abstract: A thereminist robot has a characteristic model of theremin and is capable of performing in response to an environment of theremin performance by calibrating the characteristic model before the performance. A robot 10 has a first arm 12, a second arm 11, and a pitch model for indicating an arm position corresponding to a pitch of the theremin The robot 10 plays the theremin by moving the first arm 12 to the arm position corresponding to a musical note based on the target note and the pitch model. The robot further has a parameter adjustment unit for adjusting parameters of the pitch model that change depending on environments surrounding the theremin.

Abstract: A robotic system includes a dexterous robot and a controller. The robot includes a plurality of robotic joints, actuators for moving the joints, and sensors for measuring a characteristic of the joints, and for transmitting the characteristics as sensor signals. The controller receives the sensor signals, and is configured for executing instructions from memory, classifying the sensor signals into distinct classes via the state classification module, monitoring a system state of the robot using the classes, and controlling the robot in the execution of alternative work tasks based on the system state. A method for controlling the robot in the above system includes receiving the signals via the controller, classifying the signals using the state classification module, monitoring the present system state of the robot using the classes, and controlling the robot in the execution of alternative work tasks based on the present system state.

Abstract: A robotic system that includes a mobile robot linked to a plurality of remote stations. One of the remote stations includes an arbitrator that controls access to the robot. Each remote station may be assigned a priority that is used by the arbitrator to determine which station has access to the robot. The arbitrator may include notification and call back mechanisms for sending messages relating to an access request and a granting of access for a remote station.

Abstract: A robotic system includes a robotic mechanism responsive to velocity control signals, and a permissible workspace defined by a convex-polygon boundary. A host machine determines a position of a reference point on the mechanism with respect to the boundary, and includes an algorithm for enforcing the boundary by automatically shaping the velocity control signals as a function of the position, thereby providing smooth and unperturbed operation of the mechanism along the edges and corners of the boundary. The algorithm is suited for application with higher speeds and/or external forces. A host machine includes an algorithm for enforcing the boundary by shaping the velocity control signals as a function of the reference point position, and a hardware module for executing the algorithm. A method for enforcing the convex-polygon boundary is also provided that shapes a velocity control signal via a host machine as a function of the reference point position.

Abstract: An element 22 which determines a manipulation amount for controlling a motion state of each joint 4 of a robot 1 calculates a pseudo inverse matrix A* used for calculating the manipulation amount, using a value of an adjustment parameter k determined so that an absolute value of a determinant DET is equal to or more than a predetermined threshold. Setting a provisional value of the adjustment parameter k by gradually increasing the provisional value from a predetermined initial value, calculating the determinant DET using the set provisional value, and determining whether the absolute value of the calculated determinant DET is equal to or more than the predetermined threshold is repeated, and the provisional value of the adjustment parameter k when the determination result is true is determined as the value of the adjustment parameter k used for the calculation of the pseudo inverse matrix A*.

Abstract: A semiconductor wafer manufacturing apparatus is equipped with a diagnostic module for diagnosing integrity of a transfer robot. The diagnostic module is attached to one side of a semiconductor wafer transfer chamber provided with the transfer robot, which side is also used for the purpose of maintenance, for example. One or more sensors are installed in the diagnostic module so that when the transfer robot is inserted into the diagnostic module, the position or shape of each end effector of the transfer robot is detected and compared against a pre-registered normal condition, thereby diagnosing the integrity of the end effector of the transfer robot, while performing wafer processing.

Abstract: Disclosed are a path planning apparatus of a robot, which generates a path plan to control movements of the robot, and a method thereof. An improved RRT algorithm is employed, when a tree is extended in a configuration space so as to satisfy a constraint, and thus steeply bent or roundabout portions of the tree are reduced.

Abstract: A behavior control system capable of controlling the behavior of an agent (robot) such that the agent securely applies a force to a moving object. The behavior control system calculates the degree of overlapping of a time-series probability density distribution between a predicted position trajectory of an object (ball) and a position trajectory candidate of a counter object (racket). Further, a behavior plan of the agent (robot) is generated such that the counter object is moved according to a desired position trajectory, which is a mean position trajectory or a central position trajectory of a position trajectory candidate of the counter object which has the highest degree of overlapping with the predicted position trajectory of the object among a plurality of position trajectory candidates of the counter object.

Abstract: Aspects of the subject technology relate to a robotic finger digit including a distal finger joint coupled between a distal finger part and a middle finger part, a middle finger joint coupled between the middle finger part and a proximal finger part and an extend tendon coupled at a first end to the distal finger joint, and coupled at a second end to an actuation device. In certain aspects, the robotic finger can further include a flex tendon coupled at a first end to the distal finger joint, and coupled at a second end to the actuation device, wherein the actuation device is configured to move the extend tendon and the flex tendon substantially the same distance in order to flex and/or extend the robotic finger digit.

Abstract: A method of navigating an autonomous mobile device to a base station is provided. In the method, when a detector detects a navigating signal sent out by the base station, the mobile device rotates in a first direction until the detector fails to detect the navigating signal, and a first time point is set at this time. Then, the mobile device rotates in a second direction opposite to the first direction until the detector fails to detect the navigating signal, and a second time point is set at this time. Afterward, the mobile device rotates in the first direction by a time computed based on the first and second time points to make the detector face the base station, and then, moves toward a direction pointed by the detector.

Abstract: A method to move a person with an automated manipulator, in particular a robot, includes moving a rider receptacle for a person with the manipulator, and determining an acceleration variable of this movement before and/or during the execution of this movement and comparing the acceleration variable with a predetermined acceleration variable and/or adapting the movement to a predetermined acceleration variable in the event that the determined acceleration variable deviates from the predetermined acceleration variable, and/or a predetermined acceleration variable is used that includes different permissible acceleration durations that are respectively associated with a permissible acceleration value.

Abstract: In a method for controlling a manipulator, in particular a robot, a reference path is stored and reference increments are automatically determined while following the path the reference increments are determined based on the dynamics of the manipulator while following the path.

Abstract: A system of manipulators including several manipulators, namely robots and/or external axes, such as workstations or transport tracks, whereby each manipulator is controlled by a control system via communication means and is programmed to carry out a plurality of tasks. The system of manipulators is movable in a first coordinate system. A second coordinate system is defined for each manipulator, so that one part of the manipulator, e.g. its tool center point, stands still in the second coordinate system, which is movable relative to the first coordinate system.

Abstract: A work apparatus sets a virtual target point on an image plane in an imaging apparatus, and obtains a plurality of coordinate values of a moving unit at which a work reference point of a work unit and the virtual target point are caused to match in an image captured by the imaging apparatus. Further, the work apparatus obtains, in the image, coordinate values of the moving unit at which a position of light projection by a distance information obtaining unit and the virtual target point are caused to match, and a plurality of pieces of distance information obtained from the distance information obtaining unit at those coordinate positions. Then, the work apparatus calculates, based on the plurality of coordinate values and the plurality of pieces of distance information obtained through the above processing, a calibration parameter for the moving unit and the distance information obtaining unit.

Abstract: A decision mechanism is configured to decide on at least one prospective action of a robot from set of actions by: computing a prior probabilistic representation of a prior environment state; updating the prior probabilistic representation with targets of a new observation on reducing at least one uncertainty in a posterior probabilistic representation of a posterior environment state to be reached after an appliance of the at least one prospective action, the posterior probabilistic representation resulting from the updating; determining an information gain between the prior probabilistic representation and the posterior probabilistic representation by use of at least one information theoretic measure; evaluating the at least one prospective action by adding costs of executing the at least one prospective action to the information gain. Furthermore, an improved action planning for robots is provided and can be implemented in various robots investigating scenes for their actions.

Abstract: Disclosed herein are a robot generating a message using a robot hand, and a control method thereof. When a user types characters using a robot hand, a hand body part and a finger part of the robot hand output displacement signals and a command reading unit accordingly generates a message corresponding to the displacement signals. The message is transmitted to a robot controlling unit. In addition, the message is outputted by sound or displayed to be easily checked by the user.

Abstract: A robotic system includes a robot having a total number of degrees of freedom (DOF) equal to at least n, an underactuated tendon-driven finger driven by n tendons and n DOF, the finger having at least two joints, being characterized by an asymmetrical joint radius in one embodiment. A controller is in communication with the robot, and controls actuation of the tendon-driven finger using force control. Operating the finger with force control on the tendons, rather than position control, eliminates the unconstrained slack-space that would have otherwise existed. The controller may utilize the asymmetrical joint radii to independently command joint torques. A method of controlling the finger includes commanding either independent or parameterized joint torques to the controller to actuate the fingers via force control on the tendons.

Abstract: Disclosed is a teaching and playback method using a redundancy resolution parameter determined in conjunction with a joint structure, for a robot, and a method to apply analytic inverse kinematics to a robot having an elbow with an offset and a computer-readable medium of controlling the same. A reference plane variable with the joint structure is generated and an angle between the reference plane and an arm plane of the robot is used as the redundancy resolution parameter. The robot is taught and its operation is played back in differential inverse kinematics or analytic inverse kinematics using the resolution redundancy parameter.

Abstract: A moving robot and its operation method are disclosed. The moving robot includes a moving body/object sensing unit that senses a movement of a human body within a certain distance, a traveling unit that controls a traveling speed and direction, and a controller that outputs a control signal for controlling the traveling speed according to pre-set data to the traveling unit. In a state that the moving robot performs a cleaning operation while moving its locations, when a movement of a human body is sensed by the moving body/object sensing unit, the traveling speed is reduced to allow the user to easily control the external operation, and the efficiency can be increased by utilizing the moving body/object sensing unit for operations of different modes.

Abstract: Disclosed are a robot, which performs cooperative work with a plurality of robot manipulators through impedance control, and a method of controlling cooperative work of the robot. The method includes calculating absolute coordinate positions of end effectors, respectively provided at a plurality of manipulators to perform the work; calculating a relative coordinate position from the absolute coordinate positions of the end effectors; calculating joint torques of the plurality of manipulators using the relative coordinate position; and controlling the cooperative work of the plurality of manipulators according to the joint torques.

Abstract: A control device for a robot determines, as a desired driving force to be imparted to a joint, a component value corresponding to the displacement amount of each joint out of a desired generalized force vector ?cmd that satisfies the relationship indicated by expression 01 given below by using basic parameter group of M, N, and G, Jacobian matrixes Jc and Js, a desired value ?C of the motion acceleration of a contact portion representative element representing a motion of a contact portion of a robot 1, generalized variable observation information, and a desired value ?S? of a first-order differential value of a predetermine type of state amount, and then controls the operation of an actuator of the robot 1 on the basis of the determined desired driving force.

Abstract: A robotic system implements a collision avoidance scheme and includes a first robotic manipulator and a first controller configured to control the first robotic manipulator for movement along a first pre-planned actual path. A second controller is configured to control movement of a second robotic manipulator for movement along a second pre-planned intended path and deviating therefrom to move in a dodging path away from the first pre-planned actual path based upon determining a potential collision with the first robotic manipulator without prior knowledge of the first pre-planned actual path.

Abstract: A robotic system that includes a mobile robot linked to a plurality of remote stations. One of the remote stations includes an arbitrator that controls access to the robot. Each remote station may be assigned a priority that is used by the arbitrator to determine which station has access to the robot. The arbitrator may include notification and call back mechanisms for sending messages relating to an access request and a granting of access for a remote station.

Abstract: The invention refers to a method for controlling the effector trajectory from a current state to a target state. First invariant control parameters of the trajectory are determined. The effector trajectory is then represented in a task description being void of the invariant control parameters. The effector trajectory is controlled on the basis of this task description. The invention further refers to a method for controlling the effector trajectory wherein the effector trajectory is calculated by mapping increments from a control parameter space on a configuration space. The dimensional difference between the configuration space and the control parameter space leaves redundant degrees of freedom of a Null space. The degrees of freedom of the Null space are increased using a task description being void of invariant control parameters.

Abstract: A robot hand has a pipe which is sufficiently flexible to allow a change in the cross-sectional area thereof according to the pressure of a fluid, thereby permitting a higher degree of freedom of the layouts of the pipe and a master cylinder connected through the pipe. Moreover, considerations are given to a change in the cross-sectional area of the pipe caused by a change in the pressure of the fluid in the pipe, thus making it possible to measure the position of a slave piston with high accuracy.

Abstract: In a method, device and in a non-transitory computer-readable storage medium for computer-assisted generation of a manipulator path of a computer-controlled manipulator, a processor is loaded with a virtual tool and generates a virtual tool path based in a virtual component and the loaded virtual tool. The processor is also loaded with a virtual manipulator kinematic and generates a virtual manipulator path based on the virtual tool path and the virtual manipulator kinematic.

Abstract: A finite state machine (FSM)-based biped robot, to which a limit cycle is applied to balance the robot right and left on a two-dimensional space, and a method of controlling balance of the robot. In order to balance an FSM-based biped robot right and left on a two-dimensional space, control angles to balance the robot according to states of the FSM-based biped robot are set. The range of the control angles is restricted to reduce the maximum right and left moving distance of the biped robot and thus to reduce the maximum right and left moving velocity of the biped robot, thereby reducing the sum total of the moments of the biped robot and thus allowing the ankles of the biped robot to balance the biped robot to be controlled, and causing the soles of the feet of the biped robot to parallel contact the ground.

Abstract: An finite state machine (FSM)-based biped walking robot, to which a limit cycle is applied to balance the robot right and left on a two-dimensional space, and a method of controlling balance of the robot. In order to balance an FSM-based biped walking robot right and left on a two-dimensional space, control angles to balance the robot according to states of the FSM-based biped walking robot are set, and the control angles are controlled using a sinusoidal function to allow relations between the control angles and control angular velocities to form a stable closed loop within a limit cycle, thereby allowing the biped walking robot to balance itself while changing its supporting foot and thus to safely walk without falling down.

Abstract: A motion path search device includes a motion space identification unit which identifies, as first spaces, three-dimensional spaces passed through by a movable part in direct teaching operations performed by an operator, and a spatial difference calculation unit that calculates a first differential space that is a part of one of the first spaces identified as a result of one of the direct teaching operations and that has no overlap with another of the first spaces identified as a result of another of the direct teaching operations that precedes the one of the direct teaching operations. A feedback unit provides the operator with information regarding the first differential space, and a path search unit searches for a motion path of the movable part within a first accessible space resulting from combining the first spaces after the direct teaching operations.

Abstract: Methods and computer program products for generating robot grasp patterns are disclosed. In one embodiment, a method for generating robot grasp patterns includes generating a plurality of approach rays associated with a target object. Each approach ray of the plurality of approach rays extends perpendicularly from a surface of the target object. The method further includes generating at least one grasp pattern for each approach ray to generate a grasp pattern set of the target object, calculating a grasp quality score for each individual grasp pattern of the grasp pattern set, and comparing the grasp quality score of each individual grasp pattern with a grasp quality threshold. The method further includes selecting individual grasp patterns of the grasp pattern set having a grasp quality score that is greater than the grasp quality threshold, and providing the selected individual grasp patterns to the robot for on-line manipulation of the target object.

Abstract: A robotic system includes a robot having manipulators for grasping an object using one of a plurality of grasp types during a primary task, and a controller. The controller controls the manipulators during the primary task using a multiple-task control hierarchy, and automatically parameterizes the internal forces of the system for each grasp type in response to an input signal. The primary task is defined at an object-level of control, e.g., using a closed-chain transformation, such that only select degrees of freedom are commanded for the object. A control system for the robotic system has a host machine and algorithm for controlling the manipulators using the above hierarchy. A method for controlling the system includes receiving and processing the input signal using the host machine, including defining the primary task at the object-level of control, e.g., using a closed-chain definition, and parameterizing the internal forces for each of grasp type.

Abstract: A robotic hand assembly comprising: a hand section comprising: at least one digit provided with at least one actuatable joint; and a control section comprising: at least one actuation device, the at least one actuation device comprising: a sensing module configured to sense a force applied to a tendon coupled at a first end to the at least one actuatable joint; and an actuation module configured to actuate the at least one actuatable joint.

Abstract: A robotic system includes a robot adapted for moving a payload in proportional response to an input force from an operator, sensors adapted for measuring a predetermined set of operator input values, including the input force, and a controller. The controller determines a changing stiffness value of the operator using set of operator input values, and automatically adjusts a level of control sensitivity over the robot using the stiffness value. The input values include the input force, a muscle activation level of the operator, and a position of the operator. A method of controlling the robot includes measuring the operator input values using the plurality of sensors, processing the input values using the controller to thereby calculate the stiffness value, and automatically adjusting the level of control sensitivity over the robot using the stiffness value. A specific operator may be identified, with control sensitivity being adjusted based on the identity.