Training on the Job — Collecting Experience with Hierarchical Hybrid Automata (bibtex)
by A Kirsch and M Beetz
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.
Reference:
Training on the Job — Collecting Experience with Hierarchical Hybrid Automata (A Kirsch and M Beetz), In Proceedings of the 30th German Conference on Artificial Intelligence (KI-2007) (J. Hertzberg, M. Beetz, R. Englert, eds.), 2007. 
Bibtex Entry:
@inproceedings{kirsch_training_2007,
 author = {A Kirsch and M Beetz},
 title = {Training on the Job — Collecting Experience with Hierarchical Hybrid
	Automata},
 booktitle = {Proceedings of the 30th German Conference on Artificial Intelligence
	({KI-2007)}},
 year = {2007},
 editor = {Hertzberg, J. and Beetz, M. and Englert, R.},
 pages = {473–476},
 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.},
}
Powered by bibtexbrowser
Training on the Job — Collecting Experience with Hierarchical Hybrid Automata (bibtex)
Training on the Job — Collecting Experience with Hierarchical Hybrid Automata (bibtex)
by A Kirsch and M Beetz
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.
Reference:
Training on the Job — Collecting Experience with Hierarchical Hybrid Automata (A Kirsch and M Beetz), In Proceedings of the 30th German Conference on Artificial Intelligence (KI-2007) (J. Hertzberg, M. Beetz, R. Englert, eds.), 2007. 
Bibtex Entry:
@inproceedings{kirsch_training_2007,
 author = {A Kirsch and M Beetz},
 title = {Training on the Job — Collecting Experience with Hierarchical Hybrid
	Automata},
 booktitle = {Proceedings of the 30th German Conference on Artificial Intelligence
	({KI-2007)}},
 year = {2007},
 editor = {Hertzberg, J. and Beetz, M. and Englert, R.},
 pages = {473–476},
 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.},
}
Powered by bibtexbrowser
publications

Publications