Abstract: A computer-implemented method for determining a motion trajectory for a mobile robot based on an occupancy prior indicating probabilities of presence of dynamic objects and/or individuals in a map of an environment. Occupancy priors are determined by a reward function defined by reward function parameters. The determining of the reward function parameters includes: providing semantic maps; providing training trajectories for each of semantic maps; computing a gradient as a difference between an expected mean feature count and an empirical mean feature count depending on each of the semantic maps and on each of the training trajectories, the empirical mean feature count is the average number of features accumulated over the provided training trajectories of the semantic maps, wherein the expected mean feature count is the average number of features accumulated by trajectories generated depending on the current reward function parameters; and updating the reward function parameters depending on the gradient.

Abstract: A method includes maneuvering a robot in (i) a following mode in which the robot is controlled to travel along a path segment adjacent an obstacle, while recording data indicative of the path segment, and (ii) in a coverage mode in which the robot is controlled to traverse an area. The method includes generating data indicative of a layout of the area, updating data indicative of a calculated robot pose based at least on odometry, and calculating a pose confidence level. The method includes, in response to the confidence level being below a confidence limit, maneuvering the robot to a suspected location of the path segment, based on the calculated robot pose and the data indicative of the layout and, in response to detecting the path segment within a distance from the suspected location, updating the data indicative of the calculated pose and/or the layout.

Abstract: A feature-guided scanning trajectory optimization method for a 3D measurement robot, including: building a 3D digital model of an aircraft surface; obtaining a size of the 3D digital model; extracting features to be measured; classifying the features to be measured; calculating a geometric parameter of each type of features to be measured; generating an initial scanning trajectory of each type of features to be measured; building a constraint model of the 3D measurement robot; optimizing the initial scanning trajectory into a local optimal scanning trajectory; and planning a global optimal scanning trajectory of each type of features to be measured on the aircraft surface by using a modified ant colony optimization algorithm.

Abstract: A computer-implemented method, when executed by data processing hardware of a robot having an articulated arm and a base, causes data processing hardware to perform operations. The operations include determining a first location of a workspace of the articulated arm associated with a current base configuration of the base of the robot. The operations also include receiving a task request defining a task for the robot to perform outside of the workspace of the articulated arm at the first location. The operations also include generating base parameters associated with the task request. The operations further include instructing, using the generated base parameters, the base of the robot to move from the current base configuration to an anticipatory base configuration.

Abstract: A robot control system includes circuitry configured to: determine a necessity of assisting a robot to complete an automated work, based on environment information of the robot; select a remote operator from candidate remote operators based on stored operator data in response to determining that it is necessary to assist the robot to complete the automated work; transmit the environment information to the selected remote operator via a communication network; receive an operation instruction based on the environment information from the selected remote operator via the communication network; and control the robot to complete the automated work based on the operation instruction.

Abstract: Multi-mode personal transportation and delivery devices and methods of use are disclosed herein. A device can include a communications interface, the communications interface configured to provide vehicle-to-everything communications, a device controller comprising: a processor; and a memory for storing instructions, the processor executing the instructions to: receive a first message from a service provider that the transportation device is to relocate to a location based on user demand; and activate a redistribution mode to cause the transportation device to autonomously navigate to the location.

Abstract: Various embodiments of the present technology generally relate to robotic devices and artificial intelligence. More specifically, some embodiments relate to a robotic device for picking items from a bin and perturbing items in a bin. The robotic device may include one or more picking elements and one or more perturbation elements for disturbing a present arrangement of items in the bin. In an exemplary embodiment, a perturbation element comprises a compressed air valve. In some implementations, the robotic device may also include one or more computer-vision systems. Based on image data from the one or more computer-vision systems, a strategy for picking up items from the bin is determined. When no strategies with high probability of success exist, the robotic device may perturb the contents of the bin to create new available pick-up points.

Abstract: A method for controlling a patrolling robot is provided. The method includes the steps of: acquiring, as first situation information on the patrolling robot, at least one of weight information on a support coupled to the patrolling robot and image information on the support and information on a location of the patrolling robot in a patrolling place; and determining a task and a travel route of the patrolling robot on the basis of the first situation information.

Abstract: The present application relates to a method for robot control. The method includes: obtaining at least one parameter associated with a robot to be controlled by a controller; determining a first identity of the robot based on the at least one parameter; comparing the first identity with a pre-stored second identity; and in response to the first identity matching the second identity, controlling operations of the robot with the controller. The present application further discloses detection of a mismatch between the controller and the robot in an easy, safe and convenient way.

Abstract: The present disclosure provides a method for performing a non-revisiting coverage task by a manipulator with a least number of lift-offs, and relates to the technical field of manipulator path planning. By explicitly considering lift-offs of an end-effector from a surface of an object due to kinematic constraints when the manipulator performs a task of covering the surface of the object, this method transforms a problem of coverage path design into a problem of sub-cell decomposition and solves the problem to obtain an approach for the manipulator to cover a sub-cell. The method of the present disclosure minimizes the number of lift-offs of the end-effector from the surface of the object when the manipulator performs the coverage task.

Abstract: A controller controls a motion of an object performing a task for changing a state of the object from a start state to an end state while avoiding collision of the object with an obstacle according to an optimal trajectory determined by solving an optimization problem of the dynamics of the object producing an optimal trajectory for performing the task subject to constraints on a solution of first-order stationary conditions modeling a minimum distance between the convex hull of the object and the convex hull of the obstacle using complementarity constraints.

Abstract: A mode driving assistance system for a vehicle assists a driver when the driver conducts mode driving by operating an operation member such that a traveling speed meets a time series change in the traveling speed. The operation member is disposed on a chassis dynamometer. The operation member conducts at least one of acceleration or deceleration of the vehicle. The system includes: a display that the driver can observe visually; a storage that stores a target value relating to an operation amount of the operation member in time series; a first detector that detects an actual value of the operation amount of the operation member; and a controller that displays the target value of the operation amount of the operation member stored in the storage and the actual value of the operation amount of the operation member detected by the first detector, as a time series image on the display.

Abstract: Embodiments provide functionality to prevent collisions between robots and objects. An example embodiment detects a type and a location of an object based on a camera image of the object, where the image has a reference frame. Motion of the object is then predicted based on at least one of: the detected type of the object, the detected location of the object, and a model of object motion. To continue, a motion plan for the robot is generated that avoids having the robot collide with the object based on the predicted motion of the object and a transformation between the reference frame of the image and a reference frame of the robot. The robot can be controlled to move in accordance with the motion plan or a signal can be generated that controls the robot to operate in accordance with the motion plan.

Abstract: According to one embodiment, a handling device includes: a holding part that includes two or more supporting parts and is capable of holding an object by gripping the object with the two or more supporting parts; a calculation part configured to calculate a safety factor indicating safety of a state of the holding part holding the object; and a controller configured to cause the holding part to hold the object according to the safety factor.

Abstract: A robot system includes robot bodies, operation devices each configured to accept operation and generate operational information for causing the robot body to operate, motion controllers configured to control operation of the corresponding robot body in response to the operational information, operation target selectors configured to receive an operation for selecting any of the robot bodies and request a permission to operate the selected robot body based on the operational information from the corresponding operation device, and an operation permitting device having a determinator configured to receive the permission request from the operation target selector and determine whether a permission is to be granted for the permission request. When the permission request is received, and the operation of the robot body selected by the operation target selector based on the operational information from a different operation device is permitted, the determinator prohibits the permission to the permission request.

Abstract: According to one or more embodiments of the disclosure, a first autonomous mobile robot (AMR) encounters a second AMR, while navigating a location. The first AMR receives, from the second AMR, a task list of the second AMR. The first AMR determines an adjustment to the task list of the second AMR, based in part on a comparison between the task list of the second AMR and a task list maintained by the first AMR. The first AMR sends, to the second AMR, the adjustment to the task list of the second AMR.

Abstract: A method for teaching a robot to perform an operation based on human demonstration with images from a camera. The method includes a teaching phase where a 2D or 3D camera detects a human hand grasping and moving a workpiece, and images of the hand and workpiece are analyzed to determine a robot gripper pose and positions which equate to the pose and positions of the hand and corresponding pose and positions of the workpiece. Robot programming commands are then generated from the computed gripper pose and position relative to the workpiece pose and position. In a replay phase, the camera identifies workpiece pose and position, and the programming commands cause the robot to move the gripper to pick, move and place the workpiece as demonstrated. A teleoperation mode is also disclosed, where camera images of a human hand are used to control movement of the robot in real time.

Abstract: A device and method for controlling a robotic device. The method includes: training a control model, which includes a parameter model and an object model, including: providing for each initial state-target state pair of a plurality of initial state-target state pairs a control state sequence, including states and transition states, each transition state being assigned a set of task parameters; ascertaining a set of state transition-state-state transition triples, and for each: adapting the parameter model so that the parameter model ascertains a probability distribution for each task parameter from the set of task parameters, which is assigned to the state transition following the state, adapting the object model so that the object model ascertains for each object a probability distribution for the state of the object; and controlling the robotic device with the control model using the trained parameter model and the trained object model.

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: 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.