PROJECT TITLE :

Task Parameterization Using Continuous Constraints Extracted From Human Demonstrations

ABSTRACT:

During this paper, we tend to propose an approach for learning task specifications automatically, by observing human demonstrations. Using this approach permits a robot to mix representations of individual actions to achieve a high-level goal. We have a tendency to hypothesize that task specifications contains variables that gift a pattern of amendment that's invariant across demonstrations. We tend to establish these specifications at completely different stages of task completion. Changes in task constraints permit us to spot transitions in the task description and to segment them into subtasks. We tend to extract the following task-space constraints: 1) the reference frame in that to precise the task variables; 2) the variable of interest at each time step, position, or force at the top effector; and 3) a issue that can modulate the contribution of force and position in a hybrid impedance controller. The approach was validated on a seven-degree-of-freedom Kuka arm, performing 2 completely different tasks: grating vegetables and extracting a battery from a charging stand.