Training on the Job — Collecting Experience with Hierarchical Hybrid Automata - Archive ouverte HAL Access content directly
Conference Papers Year : 2007

Training on the Job — Collecting Experience with Hierarchical Hybrid Automata

Abstract

We propose a novel approach to experience collection for autonomous service robots performing complex activities. This approach enables robots to collect data for many learning problems at a time, abstract it and transform it into information specific to the learning tasks and thereby speeding up the learning process. The approach is based on the concept of hierarchical hybrid automata, which are used as transparent and expressive representational mechanisms that allow for the specification of these experience related capabilities independent of the program itself. The suitability of the approach is demonstrated through experiments in which a robot doing household chore performs experience-based learning.
Fichier principal
Vignette du fichier
kirsch07training.pdf (254.15 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01361444 , version 1 (07-09-2016)

Identifiers

Cite

Alexandra Kirsch, Michael Beetz. Training on the Job — Collecting Experience with Hierarchical Hybrid Automata. 30th German Conference on Artificial Intelligence (KI-2007), Sep 2007, Osnabrück, Germany. pp.473-476, ⟨10.1007/978-3-540-74565-5_43⟩. ⟨hal-01361444⟩
60 View
46 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More