Housekeeping with Multiple Autonomous Robots: Knowledge Representation and Automated Reasoning for a Tightly Integrated Robot Control Architecture. Aker, E., Erdogan, A., Erdem, E., & Patoglu, V. In Workshop on Knowledge Representation for Autonomous Robots, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2011), 2011.
abstract   bibtex   2 downloads  
We embed knowledge representation and automated reasoning in each level of the classical 3-layer robot control architecture, in such a way as to tightly integrate these layers. At the high-level, we represent not only actions and change but also commonsense knowledge in the action description language~p̧lus. Geometric reasoning is lifted to the high-level by embedding motion planning in the domain description, using external predicates. Then a discrete plan is computed for each robot, using the causal reasoner CCALC. At the mid-level, if a continuous trajectory is not computed by a motion planner because the discrete plan is not feasible at the continuous-level, then formal queries are asked to the causal reasoner to find a different plan subject to some (temporal) conditions represented as formulas. At the low-level, if the plan execution fails, then a new continuous trajectory is computed by a motion planner at the mid-level or a new discrete plan is computed using an automated reasoner at the high-level. We apply this tightly integrated robot control architecture in a housekeeping domain with multiple autonomous robots, and illustrate this application with a simulation.
@InProceedings{Aker2011,
	booktitle = {Workshop on Knowledge Representation for Autonomous Robots, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2011)},
	author = {Erdi Aker and Ahmetcan Erdogan and Esra Erdem and Volkan Patoglu},
	title = {Housekeeping with Multiple Autonomous Robots: Knowledge Representation and Automated Reasoning for a Tightly Integrated Robot Control Architecture},
	year = {2011},
	abstract = {We embed knowledge representation and automated reasoning in each level of the classical 3-layer robot control architecture, in such a
way as to tightly integrate these layers. At the high-level, we represent not only actions and change but also commonsense knowledge
in the action description language~\cplus. Geometric reasoning is lifted to the high-level by embedding motion planning in the domain
description, using external predicates. Then a discrete plan is computed for each robot, using the causal reasoner CCALC.  At the
mid-level, if a continuous trajectory is not computed by a motion planner because the discrete plan is not feasible at the
continuous-level, then formal queries are asked to the causal reasoner to find a different plan subject to some (temporal)
conditions represented as formulas. At the low-level, if the plan execution fails, then a new continuous trajectory is computed by a motion planner at the mid-level or a new
discrete plan is computed using an automated reasoner at the high-level. We apply this tightly integrated robot control
architecture in a housekeeping domain with multiple autonomous robots, and illustrate this application with a simulation. }
}

Downloads: 2