Exploration of Indoor Environments through Predicting the Layout of Partially Observed Rooms
Contributo in Atti di convegno
Data di Pubblicazione:
2021
Citazione:
Exploration of Indoor Environments through Predicting the Layout of Partially Observed Rooms / M. Luperto, L. Fochetta, F. Amigoni - In: AAMAS '21: Proceedings / [a cura di] F. Dignum, A. Lomuscio, U. Endriss, A. Nowé. - [s.l] : ACM, 2021. - ISBN 978-1-4503-8307-3. - pp. 836-843 (( Intervento presentato al 20. convegno International Conference on Autonomous Agents and Multiagent Systems tenutosi a Virtual nel 2021 [10.5555/3463952.3464052].
Abstract:
We consider exploration tasks in which an autonomous mobile robot incrementally builds maps of initially unknown indoor environments. In such tasks, the robot makes a sequence of decisions on where to move next that, usually, are based on knowledge about the observed parts of the environment. In this paper, we present an approach that exploits a prediction of the geometric structure of the unknown parts of an environment to improve exploration performance. In particular, we leverage an existing method that reconstructs the layout of an environment starting from a partial grid map and that predicts the shape of partially observed rooms on the basis of geometric features representing the regularities of the indoor environment. Then, we originally employ the predicted layout to estimate the amount of new area the robot would observe from candidate locations in order to inform the selection of the next best location and to early stop the exploration when no further relevant area is expected to be discovered. Experimental activities show that our approach is able to exploit the predicted layout of partially observed rooms in order to speed up the exploration.
Tipologia IRIS:
03 - Contributo in volume
Keywords:
Inaccurate knowledge; Map prediction; Robot exploration
Elenco autori:
M. Luperto, L. Fochetta, F. Amigoni
Link alla scheda completa:
Titolo del libro:
AAMAS '21: Proceedings