Learning 6-D compliant motion primitives from demonstration
We present a novel method for learning 6-D compliant motions from demonstration. The key advantage of our learning method compared to current Learning from Demonstration (LfD) methods is that we learn to take advantage of existing mechanical gradients (such as chamfers) with compliance to perform in-contact motions consisting of both translation and rotation, as in aligning workpieces or attaching hose couplers. We find the desired direction, which leads the robot's end-effector to the location shown in the demonstration either in free space or in contact, separately for translational and rotational motions. The key idea is to first compute a set of directions which would result in the observed motion at each timestep during a demonstration. By taking an intersection over all such sets from a demonstration we find a single desired direction which can reproduce the demonstrated motion. Finding the number of compliant axes and their directions in both rotation and translation is based on the assumption that in the presence of a desired direction of motion, all other observed motion is caused by the contact force of the environment, signalling the need for compliance. We evaluate the method on a KUKA LWR4+ robot with test setups imitating typical tasks where a human would use compliance to cope with positional uncertainty. Results show that the method can successfully learn and reproduce compliant motions by taking advantage of the geometry of the task, therefore reducing the need for initial accuracy.
READ FULL TEXT