Abstract: A system for parameter tuning for robotic manipulators is provided. The system includes an interface configured to receive a task specification, a plurality of physical parameters, and a plurality of control parameters, wherein the interface is configured to communicate with a real-world robot via a robot controller. The system further includes a memory to store computer-executable programs including a robot simulation module, a robot controller, and an auto-tuning module a processor, in connection with the memory. In this case, the processor is configured to acquire, in communication with the real-world robot, state values of the real-world robot, state values of the robot simulation module, simultaneously update, by use of a predetermined optimization algorithm with the auto-tuning module, an estimate of one or more of the physical, and said control parameters, and store the updated parameters.

Abstract: A visual navigation inspection and obstacle avoidance method for a line inspection robot is provided. The line inspection robot is provided with a motion control system, a visual navigation system and an inspection visual system; and the method comprises the following steps: (1) according to an inspection image, the inspection visual system determining and identifying the type of a tower for inspection; (2) the visual navigation system shooting a visual navigation image in real time to obtain the type of a target object; (3) coarse positioning; (4) accurate positioning; and (5) according to the type of the tower and the type of the target object, the visual navigation system sending a corresponding obstacle crossing strategy to the motion control system, such that the inspection robot completes obstacle crossing. The inspection and obstacle avoidance method is real-time and efficient.

Abstract: A legged robot having a frame with a plurality of links in mechanical communication with plurality of brackets, the frame forming a front, back, top, bottom, and sides, legs in mechanical communication with one or more of the plurality of brackets, each leg having a knee motor, an abduction motor, and a hip motor, a computer module in mechanical communication with one or more of the plurality of brackets and in electrical communication with the legs, and a power module in mechanical communication with one or more of the plurality of brackets and in electrical communication with the legs and the computer module.

Abstract: A robotic arm system includes first robotic arm, second robotic arm and main controller. The first robotic arm and the second robotic arm are configured to grab object. The main controller is configured to: determine whether first force vector of first force applied by the first robotic arm to the object is equal to second force vector of second force applied by the second robotic arm to the object; when the first force vector and the second force vector are not equal, obtain a first difference between the first force vector and the second force vector; and according to the first difference, change at least one of the first force applied by the first robotic arm to the object and the second force applied by the second robotic arm to the object so that the first force vector and the second force vector are equal.

Abstract: A robot control method for a robot performing an insertion operation of inserting a second target object with force control into a first target object conveyed by a conveyor device is provided. The robot control method includes: a follow step of causing the second target object to follow the first target object from an operation start location, based on a conveyance speed of the first target object; a contact step of bringing the second target object into contact with the first target object, the second target object being in a tilted attitude in relation to the first target object, with the force control; an attitude change step of changing the attitude of the second target object in such a way that the tilt in relation to the first target object is eliminated, while pressing the second target object against the first target object, with the force control; and an insertion step of inserting the second target object into the first target object.

Abstract: A failure prediction method of predicting a failure of a component of a robot including a robot arm having the component and a detection section that detects information on vibration characteristics when the robot arm moves, includes generating a failure prediction model for prediction of the failure of the component by machine learning based on the information on vibration characteristics, and predicting the failure of the component based on an estimated value of failure prediction output by the generated failure prediction model when the information on vibration characteristics is input to the generated failure prediction model.

Abstract: A sampling method includes: obtaining topographical information about a predetermined wide area by using a first sensor on a work machine; selecting a candidate area within the wide area, the candidate area is less than an area of the wide area, and setting a movement route based on the information about the wide area, the movement route allows a distal end portion of an arm provided on the work machine to reach a preparation position without coming into contact with an obstacle, the preparation position being located above the candidate area; moving the distal end portion of the arm along the movement route to the preparation position, and obtaining topographical information about the candidate area by using a second sensor on the distal end portion of the arm; and specifying a sampling point based on the information about the candidate area and performing sampling at the specified sampling point.

Abstract: A procedure for a positioning of an aircraft is provided. An airspace user initiates using of a service provided by an air traffic manager and sends identifying data to the air traffic manager, the air traffic manager registers an aircraft identifier, carries out a standalone positioning. As the aircraft identifier, an International Mobile Subscriber Identity (IMSI) number of a code card connected to a switched on on-board device and placed on board the aircraft is used, the airspace user logs in to a cellular network contracted by the air traffic manager, time stamps emitted by at least three cellular base stations are recorded, then observed time difference of arrival data proportionate to a distance from the at least three cellular base stations are calculated, the observed time difference of the arrival data are sent through the cellular network to a location based server.

Abstract: A ground reaction force load difference calculation unit configured to calculate a ground reaction force load difference that is an amount of a load relief for a user, on the basis of a first measured value that a weight, based on a weight of the user and a weight of the load reduction device that reduces a load on the user and has a mechanism that holds luggage and is at least worn by the user, is transmitted to a ground contact surface and of a second measured value that a weight based on the weight of the user is transmitted to the ground contact surface; and a torque control unit configured to control, on the basis of the ground reaction force load difference, torque that is output by the load reduction device to reduce the load on the user at an joint of each leg of the user.

Abstract: A handling appliance, in particular a robot, includes at least one handling device that is movable in at least one direction of movement, a collision protection device configured for limiting contact forces due to collisions of the handling device with objects, and an acquisition device. The collision protection device includes a kinematic system that mechanically enables a relative movement of the handling device relative to the carrier of the handling device and that can be inhibited by at least one actuator device. The acquisition device determines forces acting on the actuator device and/or the handling device and on components of the collision protection device decoupled by the actuator device, and the collision protection device accounts for the forces and, via the actuator device, in the absence of a collision prevents, and in the case of a collision triggers and/or enables, relative movement of the handling device relative to the carrier.

Abstract: The present disclosure relates to a method of controlling movement of a cart in response to a change in a travel surface using artificial intelligence and a cart implementing the same, and in a cart robot of one embodiment, an IMU sensor senses a change in a travel surface, and an obstacle sensor senses a distance from an installed object placed in a direction of an advance of the cart robot, to control a moving part of the cart robot.

Abstract: A fitting method includes (a) detecting a first position as a position where fitting of a first object and a second object is determined, (b) moving the first object from the first position toward a determination direction different from a fitting direction and detecting a second position as a position where magnitude of a force applied to the first object reaches a predetermined reference value, and (c) determining that a fitting condition of the first object and the second object is good when a predetermined determination condition including a condition that the second position is within an acceptable position range set according to the first position is satisfied.

Abstract: Provided is a process including: obtaining a first set of one or more images generated via an optical gas imaging (OGI) camera and a second set of one or more images generated via a second camera, wherein the first set and the second set correspond to a first location of a plurality of locations in a facility; classifying, via a convolutional neural network (CNN), the first set of one or more images according to whether the one or more images depict a gas leak; and storing a result of classifying the first set in memory.

Abstract: Provided is a control device capable of controlling the operation of a control target according to a detected external force. A control device (200) includes a control unit (210-1) that compares a first external force detected by a force sensor provided in a control target and a second external force estimated on the basis of a torque detected by a torque sensor provided in an a movable portion of the control target, the movable portion enabling the force sensor to be movable, and controls the operation of the control target by correcting a torque command value on the basis of a result of the comparison.

Abstract: Implementations are provided for increasing realism of robot simulation by injecting noise into various aspects of the robot simulation. In various implementations, a three-dimensional (3D) environment may be simulated and may include a simulated robot controlled by an external robot controller. Joint command(s) issued by the robot controller and/or simulated sensor data passed to the robot controller may be intercepted. Noise may be injected into the joint command(s) to generate noisy commands. Additionally or alternatively, noise may be injected into the simulated sensor data to generate noisy sensor data. Joint(s) of the simulated robot may be operated in the simulated 3D environment based on the one or more noisy commands. Additionally or alternatively, the noisy sensor data may be provided to the robot controller to cause the robot controller to generate joint commands to control the simulated robot in the simulated 3D environment.

Abstract: Method and robot arm, where the motor torques of the joint motors of a robot arm are controlled based on a static motor torque indicating the motor torque needed to maintain the robot arm in a static posture, where the static motor torque is adjusted in response to a change in posture of the robot arm caused by an external force different from gravity applied to the robot arm. Further the motor torque of the joint motors is controlled based on an additional motor torque obtained based on a force-torque provided to the robot tool flange, where the force-torque is obtained by a force-torque sensor integrated in the tool flange of the robot arm.

Abstract: A method of adjusting a force control parameter includes a first step of moving a robot arm based on first information on work start position and orientation of the robot arm and a candidate value of a force control parameter, and acquiring second information on a working time taken for the work and third information on a force applied to the robot arm during the work, and a second step of acquiring an updated value obtained by updating of the candidate value of the force control parameter based on the acquired second information and third information, wherein the first step and the second step are repeatedly performed with noise added to the first information until the acquired working time or force applied to the robot arm converges, and a final value of the force control parameter is obtained.

Abstract: The present disclosure discloses a neural network adaptive tracking control method for joint robots, which proposes two schemes: robust adaptive control and neural adaptive control, comprising the following steps: 1) establishing a joint robot system model; 2) establishing a state space expression and an error definition when taking into consideration both the drive failure and actuator saturation of the joint robot system; 3) designing a PID controller and updating algorithms of the joint robot system; and 4) using the designed PID controller and updating algorithms to realize the control of the trajectory motion of the joint robot. The present disclosure may solve the following technical problems at the same time: the drive saturation and coupling effect in the joint system, processing parameter uncertainty and non-parametric uncertainty, execution failure handling during the system operation, compensation for non-vanishing interference, and the like.

Abstract: A control apparatus of a robot may include a state obtaining unit configured to obtain state observation data including flexible related observation data, which is observation data regarding a state of at least one of a flexible portion, a portion of the robot on a side where an object is gripped relative to the flexible portion, and the gripped object; and a controller configured to control the robot so as to output an action to be performed by the robot to perform predetermined work on the object, in response to receiving the state observation data, based on output obtained as a result of inputting the state observation data obtained by the state obtaining unit to a learning model, the learning model being learned in advance through machine learning and included in the controller.

Abstract: Candidate grasping models of a deformable object are applied to generate a simulation of a response of the deformable object to the grasping model. From the simulation, grasp performance metrics for stress, deformation controllability, and instability of the response to the grasping model are obtained, and the grasp performance metrics are correlated with robotic grasp features.