Publication
Planning surface cleaning tasks by learning uncertain drag actions outcomes
Conference Article
Conference
ICAPS Workshop on Planning and Robotics (PlanRob)
Edition
2013
Pages
106-111
Doc link
http://icaps13.icaps-conference.org/wp-content/uploads/2013/05/planrob13proceedings.pdf
File
Authors
Projects associated
Abstract
A method to perform cleaning tasks is presented where a robot manipulator autonomously grasps a textile and uses different dragging actions to clean a surface. Actions are imprecise, and probabilistic planning is used to select the best sequence of actions. The characterization of such actions is complex because the initial autonomous grasp of the textile introduces differences in the initial conditions that change the efficacy of the robot cleaning actions. We demonstrate that the action outcome probabilities can be learned very fast while the task is being executed, so as to progressively improve robot performance. The learner adds only a little overhead to the system compared to the improvements obtained. Experiments with a real robot show that the most effective plan varies depending on the initial grasp, and that plans become better after only a few learning iterations.
Categories
intelligent robots, learning (artificial intelligence), manipulators, planning (artificial intelligence), uncertainty handling.
Scientific reference
D. Martínez, G. Alenyà and C. Torras. Planning surface cleaning tasks by learning uncertain drag actions outcomes, 2013 ICAPS Workshop on Planning and Robotics, 2013, Rome, pp. 106-111.
Follow us!