Automated Planning with Induced Qualitative Models in Dynamic Robotic Domains

Abstract

Various methods of learning qualitative models by autonomous robots have previously been proposed as a viable alternative to traditional numerical modeling, but an efficient way of using such models for planning still remained an open problem. This paper summarizes a doctorat thesis, which proposes a novel domain-independent qualitative approach to automated planning and execution of robotic plans. The proposed method is demonstrated in five different robotic domains. Različne metode učenja kvalitativnih modelov v avtonomni robotiki so bile v preteklosti predlagane kot možna alternativa tradicionalnemu numeričnemu modeliranju, toda učinkovit način uporabe takšnih modelov za planiranje je še vedno ostal odprt problem. Ta članek povzema doktorska disertacijo, ki predlaga nov, domensko neodvisen kvalitativen pristop k avtomatiziranemu planiranju in izvedbi robotskih planov. Disertacija predlagano metodo demonstrira v petih različnih robotskih domenah.