A coating system for applying a coating to a substrate that can be part of a wall assembly. The system includes a positioning stage and an end effector coupled at a distal end of the positioning stage, the end effector configured to apply coating to a target surface. The system can further include a computing device executing a computational planner that: generates instructions for driving the end effector and positioning stage to perform at least one coating task that includes applying coating, via the coating the end effector, to one or more substrate pieces, the generating based at least in part on obtained target surface data; and drives the end effector and positioning stage to perform the at least one coating task.

A robot motion program generating apparatus generates a motion program for moving a robot, avoiding an obstacle. The apparatus comprises a section inputting a taught trajectory of the robot, a section setting a tolerance region around the trajectory inputted by the trajectory inputting section, a section setting a motion-point group that is a collection of the motion points, by determining motion points of the robot in the tolerance region set by the region setting section, and iterating a task of connecting a source motion point to a subsequent motion point through a line segment, avoiding the obstacle, starting from one end and ending at the other end of the trajectory, and a section generating the motion program, based on the motion-point group set by the point-group setting section.

Various embodiments are related to processor subsystems of material handling systems performing methods of creating one or more case placement patterns for placement of cases on a pallet by a palletizer. A human-machine interface (HMI) is executed by the processor subsystem that provides a control affordance to a user, selection, or to provide numerical inputs, for creating or selecting pre-created patterns. The HMI is adapted to provide preview of patterns in real-time, while the patterns are created. In this regard, the preview of patterns corresponds to currently positioned representations of cases on a pallet. The HMI is also adapted to render dynamic changes on the previewed pattern as the cases are positioned on the pallet, in real world, by the palletizer.

Embodiments of the present disclosure relate to a method and apparatus of scheduling welding operations. In an embodiment of the present disclosure, the method includes identifying seams on a welding object in a three-dimensional model for the welding object based on geometry of bodies contained in the welding object. The method also includes determining a welding sequence based on the seams, welding parameters and welding process requirements. The method further includes generating an operation procedure for a welding robot based on another three-dimensional model for the welding robot, the welding sequence, robot path parameters and the welding parameters to schedule the welding operations of the welding object. With embodiments of the present disclosure, the welding procedure could be generated in an automatic way and thus a robot can be used in welding huge and complex structures or structures manufactured in a small batch so that the automatic level can be increased remarkably and the production cost can be reduced accordingly.

The present disclosure provides an information processing device including an acquisition unit, a processing unit and an output unit.

Methods and systems for distributing remote assistance to facilitate robotic object manipulation are provided herein. Regions of a model of objects in an environment of a robotic manipulator may be determined, where each region corresponds to a different subset of objects with which the robotic manipulator is configured to perform a respective task. Certain tasks may be identified, and a priority queue of requests for remote assistance associated with the identified tasks may be determined based on expected times at which the robotic manipulator will perform the identified tasks. At least one remote assistor device may then be requested, according to the priority queue, to provide remote assistance with the identified tasks. The robotic manipulator may then be caused to perform the identified tasks based on responses to the requesting, received from the at least one remote assistor device, that indicate how to perform the identified tasks.

Methods and systems for distributing remote assistance to facilitate robotic object manipulation are provided herein. Regions of a model of objects in an environment of a robotic manipulator may be determined, where each region corresponds to a different subset of objects with which the robotic manipulator is configured to perform a respective task. Certain tasks may be identified, and a priority queue of requests for remote assistance associated with the identified tasks may be determined based on expected times at which the robotic manipulator will perform the identified tasks. At least one remote assistor device may then be requested, according to the priority queue, to provide remote assistance with the identified tasks. The robotic manipulator may then be caused to perform the identified tasks based on responses to the requesting, received from the at least one remote assistor device, that indicate how to perform the identified tasks.

This disclosure relates generally to a method and system for adaptive task and motion planning (ATAMP) for object-invariant stacking operations. Traditional TAMP considering only the preconditions for execution of an object stacking task is challenging for performing all kinds of the object-invariant stacking operations The disclosed method adopts an action model for a new object and stacking is performed by drawing inferences and learning rewards using a virtual Discrete Action Space (DAS) based on a heuristically defined reward function. These inferences are utilized for identifying a plurality of new preconditions. Additionally, an efficient stacking position selection strategy is used for a n-armed bandit problem, which leads to fast convergence for performing the object-invariant stacking operations. A robotic agent repetitively interacts with an environment in real-time to adapt the action model for the new object. After adaptation, the robotic agent can perform the object-invariant stacking operations on objects with varying poses.

A method for controlling a robotic manipulator according to a task comprises accepting a feedback signal including a sequence of multi-modal observations of a state of execution of the task. The multi-modal observations are processed with a neural network having a self-attention module with a hierarchically conditioned output to produce a skill of the robotic manipulator and an action conditioned on the skill. The neural network is trained in a supervised manner with demonstration data to produce a sequence of skills and a corresponding sequence of actions for the actuators of the robotic manipulator to perform the task. The method further comprises determining one or more control commands for the one or more actuators based on the produced action and submitting the one or more control commands to the one or more actuators causing a change of the state of execution of the task.

Solutions for multi-robot configurations are co-optimized for wear, collision and optionally for performance and/or energy expenditure, across a set of non-homogenous parameters based on a set of tasks to be performed by a set of robots. Non-homogenous parameters may include two or more of: the respective base position and orientation of the robots, an allocation of tasks to respective robots, respective target sequences and/or trajectories for the robots. Such may be executed pre-runtime. Output may include for each robot: workcell layout, an ordered list or vector of targets, optionally dwell time durations at respective targets, and paths or trajectories between each pair of consecutive targets. Output may provide a complete, executable, solution to the problem, which in the absence of variability in timing, can be used to control the robots without any modification. A genetic algorithm, e.g., Differential Evolution, may optionally be used in generating a population of candidate solutions.