Planning in answer set programming while learning action costs for mobile robots
Fangkai Yang, Piyush Khandelwal, Matteo Leonetti, Peter Stone · White Rose Research Online (University of Leeds, The University of Sheffield, University of York) · 2014
For mobile robots to perform complex missions, it may be necessary for them to plan with incomplete informa-tion and reason about the indirect effects of their ac-tions. Answer Set Programming (ASP) provides an el-egant way of formalizing domains which involve indi-rect effects of an action and recursively defined fluents. In this paper, we present an approach that uses ASP for robotic task planning, and demonstrate how ASP can be used to generate plans that acquire missing information necessary to achieve the goal. Action costs are also in-corporated with planning to produce optimal plans, and we show how these costs can be estimated from expe-rience making planning adaptive. We evaluate our ap-proach using a realistic simulation of an indoor envi-ronment where a robot learns to complete its objective in the shortest time.