Abstract: A robot control device includes a log acquisitor, a first adjuster, and a second adjuster. The log acquisitor is configured to acquire operation data of a robot arm which has been operated by making a target portion of the robot arm follow a predefined target path under a feedback control. The first adjuster is configured to adjust, based on the operation data acquired by the log acquisitor, a first physical parameter for calculating a trajectory of the target portion, to reduce errors between the predefined target path and positions of the target portion. The second adjuster is configured to calculate, based on the first physical parameter adjusted by the first adjuster, the trajectory of the target portion, the second adjuster that is configured to adjust, based on the trajectory calculated by the second adjuster, a second physical parameter to be used for a feed-forward control for controlling the robot arm.

Abstract: One embodiment can provide an intelligent robotic system. The intelligent robotic system can include at least one multi-axis robotic arm, at least one gripper attached to the multi-axis robotic arm for picking up a component, a machine vision system comprising at least a three-dimensional (3D) surfacing-imaging module for detecting 3D pose information associated with the component, and a control module configured to control movements of the multi-axis robotic arm and the gripper based on the detected 3D pose of the component.

Abstract: A motor-driven power steering apparatus includes an auxiliary output generation unit configured to generate an auxiliary output of a motor by using at least one of a vehicle speed, a steering angle and a column torque; a compensation gain generation unit configured to generate a compensation gain for compensating for a steering pull of a vehicle by a rapid acceleration during a turn, by using at least one of the vehicle speed, the steering angle and the column torque; and an auxiliary output compensation unit configured to compensate for an auxiliary output by applying the compensation gain outputted by the compensation gain generation unit to the auxiliary output.

Abstract: A mobile robot is configured for operation in a commercial or industrial setting, such as an office building or retail store. The robot can patrol one or more routes within a building, and can detect violations of security policies by objects, building infrastructure and security systems, or individuals. In response to the detected violations, the robot can perform one or more security operations. The robot can include a removable fabric panel, enabling sensors within the robot body to capture signals that propagate through the fabric. In addition, the robot can scan RFID tags of objects within an area, for instance coupled to store inventory. Likewise, the robot can generate or update one or more semantic maps for use by the robot in navigating an area and for measuring compliance with security policies.

Abstract: Vehicle navigation systems and methods may generally provide navigation instructions in a vehicle. A navigation guidance session to a destination may be initiated at a telematics unit installed to the vehicle. Upon determination that the vehicle has been parked, example methods and systems may facilitate continuing the navigation guidance session when a park time duration is less than a pedestrian travel time associated with pedestrian travel from the vehicle parking location to the destination. Alternatively, terminating the navigation guidance session may be facilitated when the park time duration is at least equal to the pedestrian travel time.

Abstract: A method, apparatus, and system for adjusting inertial reference data. The inertial reference data is received from an inertial reference unit in an aircraft. Replacement magnetic navigation data is determined for the aircraft at a current position of the aircraft. Magnetic navigation data in the inertial reference data is replaced with the replacement magnetic navigation data for the aircraft to form adjusted inertial reference data. The adjusted inertial reference data is sent to a number of aircraft systems that use the adjusted inertial reference data during operation of the aircraft.

Abstract: A travel control apparatus for controlling travel of a vehicle, comprises: an acquisition unit configured to acquire external information using one of a first camera and a second camera; a specifying unit configured to specify a position of the vehicle; and a travel control unit configured to control the travel of the vehicle based on the external information acquired by the acquisition unit and the position of the vehicle specified by the specifying unit. If the acquisition unit acquires the external information using the second camera instead of the first camera, the travel control unit controls the travel of the vehicle so that participation of a driver in driving is higher than in a case in which the acquisition unit acquires the external information using the first camera.

Abstract: A machine learning system builds and uses control policies for controlling robotic performance of a task. Such control policies may be trained using targeted updates, for example by comparing two trials to identify which represents a greater degree of task success, using this to generate updates from a reinforcement learning system, and weighting the updates based on differences between action vectors of the trials.