Towards Robot Task Planning From Probabilistic Models of Human Skills
This work addresses robot task planning for robust generalization in manipulation tasks, representing an incremental advancement in skill-based motion planning.
The paper tackles the problem of enabling robots to perform complex object manipulation tasks by learning probabilistic models of human skills from demonstrations and optimizing trajectories for new environments, achieving validation in simulated and real robot experiments.
We describe an algorithm for motion planning based on expert demonstrations of a skill. In order to teach robots to perform complex object manipulation tasks that can generalize robustly to new environments, we must (1) learn a representation of the effects of a task and (2) find an optimal trajectory that will reproduce these effects in a new environment. We represent robot skills in terms of a probability distribution over features learned from multiple expert demonstrations. When utilizing a skill in a new environment, we compute feature expectations over trajectory samples in order to stochastically optimize the likelihood of a trajectory in the new environment. The purpose of this method is to enable execution of complex tasks based on a library of probabilistic skill models. Motions can be combined to accomplish complex tasks in hybrid domains. Our approach is validated in a variety of case studies, including an Android game, simulated assembly task, and real robot experiment with a UR5.