Apparatuses, systems, and techniques provide a policy that can be executed to cause a machine to move. In at least one embodiment, a first policy layer is provided to cause the machine to execute a first motion that causes the machine to accelerate to reach an unbiased state. A second policy layer is provided to cause the machine to execute a second motion without influencing the unbiased state to be reached by machine. The policy can comprise the first and second policy layers.

An automatic welding system, an automatic welding method, a welding assistance device, and a program wherein the amount of correction of the welding speed is determined on the basis of the distance between an arc and the tip of a molten pool when the distance between the arc and the tip of the molten pool is within a predetermined range in arc welding performed while alternately weaving a welding torch in the front downward direction and the rear upward direction when the welding progress direction is the frontward direction with respect to a horizontally extending groove formed between two members to be welded aligned in the vertical direction.

In an offline teaching device in the related art, in the case of changing a teaching program, even in the case of performing the same change at each teaching point, it is necessary to perform the change with respect to each teaching point. The offline teaching device of the present disclosure has a selection function, a first change function, a second change function, a welding line storage function, and a teaching program storage function. The selection function causes one welding line among a plurality of welding lines stored in the welding line storage function to be selected. The first change function causes content of a welding conditions configuring the welding line selected with the selection function to be changed. The second change function causes the welding conditions of entire instructions in the teaching program having the same welding line identification information as welding line identification information that is assigned to the welding line selected with the selection function to be changed to the same content as content changed with the first change function.

Based on data indicative of an area proximate to a robotic device, a scene is generated. Based on information from a knowledge database, a task associated with the scene is identified. A risk threshold is determined based on the scene, the task, and one or more trust thresholds. Based on the risk threshold, a ratio of sub-tasks of the task to be controlled by a user is determined. In accordance with the risk threshold, a user input is received for controlling one or more of the sub-tasks when the ratio dictates that at least one of the sub-tasks requires user intervention.

A method and dynamic learning system for providing dynamic cross learning is disclosed. The dynamic learning system identifies one or more changes in an environment in which an automated task performing device is scheduled to perform one or more activities. The dynamic learning system initiates a dynamic learning associated with the one or more changes for the automated task performing device based on pre-stored contextual information. Based on the dynamic learning, one or more actions is provided to the automated task performing device to perform the one or more activities in view of the one more changes. Therefore, the present disclosure facilitates dynamic determination and analysis of environment and situation for the automated task performing device for performing the activities. Thus, leading to dynamic decision-making to provide adjustment to the automated task performing device in any situation.

A controller for controlling an operation of a robot to execute a task is provided. The controller comprises a memory configured to store a set of dynamic movement primitives (DMPs) associated with the task. The set of DMPs comprise a set of at least two dynamical systems: a function representing point attractor dynamics and a forcing function corresponding to a learned demonstration of the task. The controller comprises a processor configured to transform the set of DMPs to a set of constrained DMPs (CDMPs) by determining a perturbation function associated with the forcing function. The perturbation function is associated with a set of operational constraints. The processor is further configured to solve, a non-linear optimization problem for the set of CDMPs based on the set of operational constraints and generate, a control input for controlling the robot for executing the task, based on the solution.

A method is provided that includes: receiving designation of one or more operation sections; generating a plurality of path candidates of a robot for a target operation section of the one or more operation sections; displaying the plurality of path candidates on a user interface; receiving a selection of one of the plurality of path candidates; and deciding the selected path candidate as the operation path of the target operation section.

In an offline teaching device in the related art, in the case of changing a teaching program, even in the case of performing the same change at each teaching point, it is necessary to perform the change with respect to each teaching point. The offline teaching device of the present disclosure has a selection function, a first change function, a second change function, a welding line storage function, and a teaching program storage function. The selection function causes one welding line among a plurality of welding lines stored in the welding line storage function to be selected. The first change function causes content of a welding conditions configuring the welding line selected with the selection function to be changed. The second change function causes the welding conditions of entire instructions in the teaching program having the same welding line identification information as welding line identification information that is assigned to the welding line selected with the selection function to be changed to the same content as content changed with the first change function.

Based on data indicative of an area proximate to a robotic device, a scene is generated. Based on information from a knowledge database, a task associated with the scene is identified. A risk threshold is determined based on the scene, the task, and one or more trust thresholds. Based on the risk threshold, a ratio of sub-tasks of the task to be controlled by a user is determined. In accordance with the risk threshold, a user input is received for controlling one or more of the sub-tasks when the ratio dictates that at least one of the sub-tasks requires user intervention.