Towards learning hierarchical skills for multi-phase manipulation tasks

Kroemer, O., Daniel, C., Neumann, G., Van Hoof, H. and Peters, J. (2015) Towards learning hierarchical skills for multi-phase manipulation tasks. In: IEEE International Conference on Robotics and Automation (ICRA), 2015, 26 - 30 May 2015, Seattle, WA.

Documents
25696 07139389.pdf

Request a copy
[img] PDF
25696 07139389.pdf - Whole Document
Restricted to Repository staff only

798kB
Item Type:Conference or Workshop contribution (Paper)
Item Status:Live Archive

Abstract

Most manipulation tasks can be decomposed into a sequence of phases, where the robot's actions have different effects in each phase. The robot can perform actions to transition between phases and, thus, alter the effects of its actions, e.g. grasp an object in order to then lift it. The robot can thus reach a phase that affords the desired manipulation. In this paper, we present an approach for exploiting the phase structure of tasks in order to learn manipulation skills more efficiently. Starting with human demonstrations, the robot learns a probabilistic model of the phases and the phase transitions. The robot then employs model-based reinforcement learning to create a library of motor primitives for transitioning between phases. The learned motor primitives generalize to new situations and tasks. Given this library, the robot uses a value function approach to learn a high-level policy for sequencing the motor primitives. The proposed method was successfully evaluated on a real robot performing a bimanual grasping task.

Keywords:Robotics, Human computer interaction
Subjects:G Mathematical and Computer Sciences > G440 Human-computer Interaction
Divisions:College of Science > School of Computer Science
Related URLs:
ID Code:25696
Deposited On:19 May 2017 14:25

Repository Staff Only: item control page