Abstract-In this work we propose an approach for learning task specifications automatically, by observing human demonstrations. Using this allows a robot to combine representations of individual actions to achieve a high-level goal. We hypothesize that task specifications consist of variables that present a pattern of change that is invariant across demonstrations. We identify these specifications at different stages of task completion. Changes in task constraints allow us to identify transitions in the task description and to segment them into sub-tasks. We extract the following task-space constraints: (1) the reference frame in which to express the task variables, (2) the variable of interest at each time step, position or force at the end effector; and (3) a factor that can modulate the contribution of force and position in a hybrid impedance controller. The approach was validated on a 7 DOF Kuka arm, performing 2 different tasks: grating vegetables and extracting a battery from a charging stand.

No abstract

The linear motor driving mechanism has been adopted as a positioning mechanism of machine tools to realize high speed and precise positioning because of friction-free and no backlash. However, when two or more linear motors are used, minute differences between the thrust forces of each motor causes the generation of micro vibration and the change of velocity of each linear motor generated by yawing around the center of gravity. This study proposes interaction-mode-control method for the machine tool table driven by three linear motors to control the three modes defined as the position of the center of gravity, bending and yawing independently. The interaction-mode-control method is a new technique for applying interaction modes defined according to the workspace to the real control system through modal conversion. From the results of simulation and experiments, it is confirmed that the three modes are controlled independently and, therefore, bending and yawing can be suppressed using interaction-mode-control. Moreover, to combine the interaction-mode-control method with disturbance observer and feedforward control, this control system has high robustness and precise positioning can be realized.