Abstract: Described herein are systems and methods that improve the success rate of relocalization and eliminate the ambiguity of false relocalization by exploiting motions of the sensor system. In one or more embodiments, during a relocalization process, a snapshot is taken using one or more visual sensors and a single-shot relocalization in a visual map is implemented to establish candidate hypotheses. In one or more embodiments, the sensors move in the environment, with a movement trajectory tracked, to capture visual representations of the environment in one or more new poses. As the visual sensors move, the relocalization system tracks various estimated localization hypotheses and removes false ones until one winning hypothesis. Once the process is finished, the relocalization system outputs a localization result with respect to the visual map.

Abstract: A system and/or method comprising providing a robotic control structure having a support structure, said support structure being adapted and configured to be selectively positionable along a prescribed path by said robotic control structure; providing a viscous material deposition system adapted and configured to control deposition of a viscous material from said viscous material deposition system; providing a load sensor associated with said robotic control structure adapted and configured to determine a load of said viscous material supported by said support structure; and positioning said support structure along said prescribed path, wherein said positioning is controlled at least in part based upon said load.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing robot planning using a process definition graph. One of the methods includes receiving an initial underconstrained process definition graph for one or more robots, wherein the process definition graph is a directed acyclic graph having constraint nodes and action nodes. A plurality of transformers are repeatedly applied to the initial process definition graph, wherein each application of a transformer generates a respective modified process definition graph according to the constraint nodes of the process definition graph, wherein applying the plurality of transformers generates a schedule that specifies which of the one or more robots are to perform which of one or more actions represented by actions nodes according to constraints imposed by the constraint nodes in the process definition graph.

Abstract: A method and system for controlling at least one effector trajectory for at least one effector of a robot for solving a predefined task are proposed. A graph of postures is acquired, and at least one of a contact constraint topology and an object constraint topology are accordingly modified. A set of constraint equations based on at least one of the modified contact constraint topology and the modified object constraint topology are generated. Constraint relaxation is performed on the generated set of constraint equations to generate a task description including the relaxed set of constraint equations. The effector trajectory is generated by applying a trajectory generation algorithm on the generated task description. An inverse kinematics algorithm is performed on the generated effector trajectory for generating a control signal, and the effector is controlled to execute the effector trajectory based on the generated control signal.

Abstract: A system that uses 3D scanning, a process agnostic pointing device used in conjunction with user input, and geometric analysis of the 3D information to create a robot program.

Abstract: A training method for a driver assistance method of a vehicle. The method includes: recording a sequence of camera images during a training run of the vehicle, guided by a user, along a desired trajectory; determining a driving corridor for the driver assistance method along the desired trajectory based on image processing of the recorded sequence of camera images; displaying the recorded sequence of camera images and/or a surrounding environment model determined based on the recorded sequence of camera images on a display, at least the determined driving corridor being displayed as an overlay superimposed on the display; and storing the driving corridor in an electronic memory of the vehicle, a recording of an input by the user for adapting a boundary of the determined driving corridor during the displaying and an adapting of the determined driving corridor based on the recorded input being carried out.

Abstract: The present invention has an object of reducing the number of resident operators in a remote driving system. A driving plan generating apparatus includes: a section selector selecting, as a selected section, at least one incompletely automated driving section; a reservation unit sounding out on reservation of a remote operation of a vehicle in the selected section; and a drive planning unit generating, based on a result of the reservation, a driving plan specifying as a driving mode of the vehicle in the selected section one of a remote driving mode in which a driving control apparatus performs at least a part of driving tasks through the remote operation performed by an operator outside the vehicle and an incompletely automated driving mode in which the driving control apparatus performs at least the part of driving tasks through an operation of a passenger in the vehicle.

Abstract: Among other things, a vehicle drives autonomously on a trajectory through a road network to a goal location based on an automatic process for planning the trajectory without human intervention; and an automatic process alters the planning of the trajectory to reach a target location based on a request received from an occupant of the vehicle to engage in a speed-reducing maneuver.

Abstract: A method for controlling movement of a robot includes inputting a first linear velocity parameter and a first angular velocity parameter, which are specified as the robot moves, into a first limit model for limiting a centripetal acceleration to correct the first linear velocity parameter and the first angular velocity parameter, thereby calculating a second linear velocity parameter and a second angular velocity parameter, inputting the second linear velocity parameter and the second angular velocity parameter into at least one of a second limit model for limiting a linear velocity and a third limit model for limiting an angular velocity to correct the second linear velocity parameter and the second angular velocity parameter, thereby calculating a third linear velocity parameter and a third angular velocity parameter, and controlling the movement of the robot based on the third linear velocity parameter and the third angular velocity parameter.

Abstract: Disclosed is a moving robot capable of recognizing a waiting line and a method for controlling the same. One embodiment provides a method for operating a moving robot, the method comprising: starting moving from a predefined moving start point toward a predefined moving end point; acquiring a waiting line region image by photographing a predefined waiting line region during the moving; searching for an end point of a waiting line formed in the waiting line region using the waiting line region image; terminating the moving when the end point of the waiting line is detected; setting an operation mode based on a length of the waiting line calculated using the end point of the waiting line; and operating in the set operation mode while returning to the moving start point.

Abstract: A robot is described. The robot includes a propulsion system, a wireless interface, a memory device, and a processor configured to execute instructions stored in the memory device. The instructions, when executed by the processor, cause the processor to determine, based upon a communication received at the wireless interface, to perform a celebration associated with a trigger event that has occurred on a casino floor and in response to determining to perform the celebration, control the propulsion system to cause the robot to perform at least a portion of the celebration.

Abstract: A driving device includes a corrector, an actuator, and a position sensor. The actuator includes a nut connected to a movable part, a ball screw shaft onto which the nut is screwed, and a pulse motor that drives to rotate the ball screw shaft. The corrector includes a correction amount map in which a position correction amount for calibrating a predictable error is mapped for each position of the movable part. The corrector estimates an ideal movement position to which the movable part moves based on a command signal and refers to the correction amount map to calculate the position correction amount corresponding to a present position detected by the position sensor. The corrector generates a correction signal by correcting the command signal so as to reduce the difference between a corrected present position obtained by correcting the present position by the position correction amount and the ideal movement position.

Abstract: A robot system includes a robot arm, encoders configured to acquire position information of the robot arm, a first control section configured to execute control processing for controlling operation of the robot arm, and a second control section provided independently from the first control section and configured to transmit a position information request signal for requesting the position information to the encoders. The second control section transmits an interrupt signal to the first control section according to the transmission of the position information request signal. The first control section executes the control processing based on the interrupt signal and the position information output from the encoders based on the position information request signal.

Abstract: A method for controlling a robot device. The method includes performing an initial training of an actor neural network by imitation learning of demonstrations, controlling the robot device by the initially trained actor neural network to generate multiple trajectories, wherein each trajectory comprises a sequence of actions selected by the initially actor neural network in a sequence of states, and observing the return for each of the selected actions, performing an initial training of a critic neural network by supervised learning, wherein the critic neural network is trained to determine the observed returns of the actions selected by the initially actor neural network, training the actor neural network and the critic neural network by reinforcement learning starting from the initially trained actor neural network and the initially trained critic neural network and controlling the robot device by the trained actor neural network and trained critic neural network.

Abstract: A control method includes an acquiring step for acquiring information concerning a plurality of end effectors and acquiring an operation program, and a driving step for driving a robot arm based on the operation program acquired in the acquiring step, wherein in the driving step, speed of a speed estimation target part is calculated, for each of the plurality of end effectors based on a detection result of the detecting section, and when it is determined that, in a result of the calculation, speed of the speed estimation target part moving at highest speed when the robot arm is driven by the operation program is equal to or higher than predetermined speed, operating speed of the robot arm is reduced.

Abstract: Systems and methods for fleet inspection and maintenance using a robot are provided. The robot may detect a maintenance issue of a vehicle of a fleet of vehicles via one or more sensors, generate a navigation route to a position proximal to the maintenance issue of the vehicle, traverse along the navigation route to the position, and execute a maintenance to rectify the maintenance issue of the vehicle. The robot may include a mobile base removably coupled to a modular platform for performing a maintenance task.

Abstract: A vehicle control system can have an in-vehicle camera that monitors a state of the driver; a center display and a meter device that notify the occupant of information; and a controller that executes automatic stop control in the case where the driver abnormality is determined. The controller can perform: a first operation to decelerate the vehicle to a specified speed when the abnormality is determined; a second operation to further decelerate and stop the vehicle after the first operation; a third operation to change a lane of the vehicle between the first operation and the second operation; and a fourth operation to move the vehicle to a road shoulder between the first operation and the second operation. The controller can notify the operation performed, and notify of a stop of the operation in the case where the operation performed is stopped.

Abstract: An autonomous tray handling robotic system is disclosed. In various embodiments, data indicating a set of output stacks to be assembled is stored, each output stack including an associated set of trays each of a corresponding tray type. Operation of one or more robots is controlled, each robot being configured to grasp, move, and place one or more trays at a time, according to a plan, to iteratively pick trays from source stacks of trays and assemble the set of output stacks, including by building each output stack by successively placing on the output stack trays picked from one or more corresponding source stacks. Each of the robots comprises a robotic arm and a tray handling end effector configured to grasp, move, and place one or more trays without assistance from another robot.

Abstract: A remote monitoring device is provided for a fleet of autonomous motor vehicles. The monitoring device is able to receive at least one piece of information from at least a first sensor monitoring the environment of a vehicle of interest, the monitoring device being able to display the information on a display screen. The monitoring device comprises: a processing module configured to determine a measuring uncertainty of the information sent by the first sensor and/or to measure a lag between the sending of the information by the first sensor and the display of the information on the display screen; and a limiting module configured to limit the piloting of said vehicle of interest by the operator as a function of the determined uncertainty and/or the measured lag.

Abstract: An origin calibration method of a manipulator is provided. The origin calibration method includes steps of: (a) controlling the manipulator to move in accordance with a movement command, and acquiring the 3D coordinates of the reference anchor points reached by the manipulator; (b) controlling the manipulator to move in accordance with the movement command while an origin of the manipulator being offset, acquiring the 3D coordinates of the actual anchor points reached by the manipulator, and acquiring a Jacobian matrix accordingly; (c) acquiring a deviation of a rotation angle of the manipulator according to the Jacobian matrix, the 3D coordinates of the reference anchor points and the actual anchor points, and acquiring a compensation angle value according to the deviation; and (d) updating the rotation angle of the manipulator according to the compensation angle value so as to update the origin of the manipulator.