Abstract: A method of training a robot to autonomously execute a robotic task includes moving an end effector through multiple states of a predetermined robotic task to demonstrate the task to the robot in a set of n training demonstrations. The method includes measuring training data, including at least the linear force and the torque via a force-torque sensor while moving the end effector through the multiple states. Key features are extracted from the training data, which is segmented into a time sequence of control primitives. Transitions between adjacent segments of the time sequence are identified. During autonomous execution of the same task, a controller detects the transitions and automatically switches between control modes. A robotic system includes a robot, force-torque sensor, and a controller programmed to execute the method.

Abstract: A method for accessing information on an electronic version of an navigation information display is described. The method includes displaying navigation information on a display of a device, the device incorporating a touch screen, sensing a user touch on the touch screen, determining, by the device, a location on the touch screen where the user touch has occurred, correlating the location on the touch screen where the user touch has occurred with a location on the navigation information display, and displaying a magnified area of a portion of the navigation information proximate the location on the touch screen where the user touch occurred.

Abstract: There is provided an electric power steering system that makes it possible to reduce an uncomfortable feeling given to a driver even when current feedback control is executed in a state where a detected steering torque value is held. The electric power steering system includes a torque sensor that outputs a detection signal corresponding to a steering torque; and a controller that controls driving of a motor. The controller computes a detected steering torque value based on the detection signal from the torque sensor, and executes current feedback control for causing an actual current value of the motor to follow a current command value based on the detected steering torque value. When the detected steering torque value is held, the controller makes a feedback gain of the current feedback control smaller than a feedback gain that is used when the detected steering torque value is not held.

Abstract: A robot cleaner includes a main body, a traveling unit installed in the main body, to move the main body, an ultrasonic sensor to emit an oscillation wave, to receive a reflection wave reflected from an object surface, and to output vibration generated by the oscillation wave and vibration generated by the reception of the reflection wave as an electrical signal, a waveform analyzer to calculate a generation time period of the electrical signal output from the ultrasonic sensor, and a controller to determine information about the object surface based on the calculated generation time period of the electrical signal, and to control movement of the traveling unit based on the information about the object surface.

Abstract: Methods and systems for determining and modeling admissible gripper forces are described. An example method may involve receiving data representative of a plurality of trajectories along which a robotic manipulator, while gripping one or more physical objects, previously moved the one or more objects without dropping the one or more objects. The method may also involve determining set of force vectors corresponding to the trajectories. The method may also involve determining a three-dimensional virtual model of the set, where boundaries of the model represent constraints on magnitudes of forces that are applied in a given direction to perform the trajectories. The method may then involve determining one or more subsequent trajectories that correspond to a subsequent set of force vectors that are within the boundaries of the model and along which the robotic manipulator can move a subsequent physical object at particular accelerations without dropping the subsequent object.

Abstract: Apparatus and methods for training of robotic devices. Robotic devices may be trained by a user guiding the robot along target trajectory using an input signal. A robotic device may comprise an adaptive controller configured to generate control commands based on one or more of the user guidance, sensory input, and/or performance measure. Training may comprise a plurality of trials. During first trial, the user input may be sufficient to cause the robot to complete the trajectory. During subsequent trials, the user and the robot's controller may collaborate so that user input may be reduced while the robot control may be increased. Individual contributions from the user and the robot controller during training may be may be inadequate (when used exclusively) to complete the task. Upon learning, user's knowledge may be transferred to the robot's controller to enable task execution in absence of subsequent inputs from the user.

Abstract: An engine diagnostic system in accordance with an embodiment not only captures the written feedback from each technician, but also tracks every step/click that the technician took during the diagnostic process and classifies those clicks into desirable or undesirable behavior patterns that indicate missing or miss-tagged content, inefficiently presented materials, or training issues such as not following troubleshooting guidance. The system provides daily updates of troubleshooting status's of diagnoses being conducted on millions of engine systems that represent a great amount of different engine models and types from around the globe, and provides data reduction techniques and metrics that guides the analyst/service engineers to high priority emerging issues reduced to specific actionable events that can be corrected and immediately monitored for their impacts on the troubleshooting system efficiency measures.

Abstract: An apparatus and a method for controlling an engine clutch of a hybrid electric vehicle may include a driving information detector to detect demand information for driving and state information of the hybrid electric vehicle, an engine clutch selectively connecting an engine and a motor generating power, and a controller receiving information from the driving information detector and changing a driving mode of the hybrid electric vehicle by controlling an operation of the engine clutch, in which the controller controls standby hydraulic pressure of the engine clutch differently according to a mode changing condition when the driving mode of the hybrid electric is changed from an Electric Vehicle (EV) mode to a Hybrid Electric Vehicle (HEV) mode.

Abstract: A robot system includes: a robot including a hand configured to hold a thin plate-shaped workpiece and an arm configured to move the hand; and a robot controller configured to control the robot. The robot controller controls the robot to perform a transfer of the workpiece at a predetermined workpiece transfer position in such a way that the hand is moved in a horizontal direction while being moved in a vertical direction after the hand has reached the workpiece transfer position.

Abstract: An electronic control system in which a sensor transmits a data to a control unit is provided. In one embodiment, the sensor includes a first detector and a second detector each converting a physical quantity of a detection target into a digital data. An output portion of the sensor outputs in turn a normal data and a monitor data associated with each other. The normal data is the digital data outputted from the first detector, and the monitor data is a reversed data of the digital data outputted from the second detector. The control unit determines that at least one of the first detector, the second detector and the output portion has failure when the reversed data does not match the normal data.

Abstract: System and methods for positioning a tool in a robotic system include determining primary position information for the tool at a first frequency and determining secondary position information for the tool at a second frequency. The tool is moved in a first position control mode and a second position control mode based on the primary position information and the secondary position information. At least one of the first and second frequencies in each of the first and second position control modes is adjusted. A difference between the first and second frequencies in the first position control mode is different than a difference between the first and second frequencies in the second position control mode.

Abstract: A joint torque computing unit computes a joint torque T1 of a joint necessary to move a joint angle to a target joint angle. A summing unit obtains a sum value U1 indicating the sum of generated forces generated at actuators, from a target stiffness. A setting unit sets a restricting coefficient h1 to a value greater than 1 when performing non-antagonistic driving, and to 1 when performing antagonistic driving. A restricting unit takes |T1|<U1×r×h1 as restricting condition where r is moment arm radius, and restricts the joint torque T1 to a range satisfying the conditions. A generated force computing unit computes the generated force of the actuators based on the restricted joint torque T1. The setting unit sets the restricting coefficient h1 to gradually near 1 when switching from non-antagonistic driving to antagonistic driving.

Abstract: A balance control apparatus of a robot and a control method thereof. The balance control method of the robot, which has a plurality of legs and an upper body, includes detecting pose angles of the upper body and angles of the plurality of joint units, acquiring a current capture point and a current hip height based on the pose angles and the angles of the plurality of joint units, calculating a capture point error by comparing the current capture point with a target capture point, calculating a hip height error by comparing the current hip height with a target hip height, calculating compensation forces based on the capture point error and the hip height error, calculating a target torque based on the calculated compensation forces, and outputting the calculated target torque to the plurality of joint units to control balance of the robot.

Abstract: A device and method for controlling a real time weaving motion are provided. In order to control operation of a robot in a working space, a main moving path of the robot in the working space is determined, a unit motion constituting the determined main moving path is generated, while a continuous motion in which a unit motion is connected, weaving that dynamically changes offset is generated, and a compensation displacement or a compensation rotation amount that is determined according to the work environment is generated. A position and a rotation amount of the robot are calculated in the working space according to at least one of the unit motion, the weaving, the compensation displacement, and the compensation rotation amount.

Abstract: A control device for controlling a robot which has a tool for holding a workpiece and a force measuring part for measuring a force acting on the tool. The control device includes a calculating part for calculating a center-of-gravity position of the workpiece, based on force data measured by the force measuring part with a plurality of postures of the robot holding the workpiece, a processing part for performing at least one of a process for estimating a holding state of the workpiece, a process for determining a type of the workpiece, and a process for testing a quality of the workpiece, based on the position of the tool and the center-of-gravity position of the workpiece, and an operating command modifying part for modifying an operating command to the robot, based on a result of the process performed by the processing part.

Abstract: Apparatus and methods for arbitration of control signals for robotic devices. A robotic device may comprise an adaptive controller comprising a plurality of predictors configured to provide multiple predicted control signals based on one or more of the teaching input, sensory input, and/or performance. The predicted control signals may be configured to cause two or more actions that may be in conflict with one another and/or utilize a shared resource. An arbitrator may be employed to select one of the actions. The selection process may utilize a WTA, reinforcement, and/or supervisory mechanisms in order to inhibit one or more predicted signals. The arbitrator output may comprise target state information that may be provided to the predictor block. Prior to arbitration, the predicted control signals may be combined with inputs provided by an external control entity in order to reduce learning time.

Abstract: A control unit (17) includes a regenerative coordination control unit (17D) and a vehicle speed calculation unit (17E). The regenerative coordination control unit (17D) performs a regeneration cooperative control to distribute the hydraulic braking force and the regenerative braking force. The vehicle speed calculation unit (17E) calculates a vehicle speed. The control unit (17) calculates a basic target driving force based on: an amount of accelerator operation detected by an accelerator operation amount detecting unit (32), and the vehicle speed calculated by the vehicle speed calculation unit (17E), and adds a value corresponding to the regenerative braking force distributed by the regenerative coordination control unit (17D) to the basic target driving force, thus obtaining a target driving force to be generated by motors (4 and 5).

Abstract: Systems and methods for sensing human muscle action and gestures in order to control machines or robotic devices are disclosed. One exemplary system employs a tight fitting sleeve worn on a user arm and including a plurality of electromyography (EMG) sensors and at least one inertial measurement unit (IMU). Power, signal processing, and communications electronics may be built into the sleeve and control data may be transmitted wirelessly to the controlled machine or robotic device.

Abstract: Lane Boundary Estimation and Host Vehicle Position and Orientation, within the host lane estimation, using V2V (vehicle to vehicle) system, are discussed here. Lane boundary detection and tracking is essential for many active safety/ADAS application. The lane boundary position enables the tracking of the host vehicle position and orientation inside the lane. It also enables classifying in-lane, adjacent lanes, and other lanes vehicles. These two functionalities (lane boundary estimation and vehicle lane classifications) enable active safety applications (such as LDW, FCW, ACC, or BSD). It also enables the lateral control of the vehicle for lane keeping assist system, or for full lateral control for automated vehicle (automated for one or multiple lane changes).

Abstract: Initial interaction between a mobile robot and at least one user is described herein. The mobile robot captures several images of its surroundings, and identifies existence of a user in at least one of the several images. The robot then orients itself to face the user, and outputs an instruction to the user with regard to the orientation of the user with respect to the mobile robot. The mobile robot captures images of the face of the user responsive to detecting that the user has followed the instruction. Information captured by the robot is uploaded to a cloud-storage system, where information is included in a profile of the user and is shareable with others.