Mobile robot exploration with potential information fields
Cita com:
hdl:2117/24948
Tipus de documentText en actes de congrés
Data publicació2013
Condicions d'accésAccés obert
Llevat que s'hi indiqui el contrari, els
continguts d'aquesta obra estan subjectes a la llicència de Creative Commons
:
Reconeixement-NoComercial-SenseObraDerivada 3.0 Espanya
Abstract
We present a mobile robot exploration strategy that computes trajectories that minimize both path and map entropies. The method evaluates joint entropy reduction and computes a potential ¿eld in robot con¿guration space using these joint entropy reduction estimates. The exploration trajectory is computed descending on the gradient of these ¿eld. The technique uses Pose SLAM as its estimation backbone. Very ef¿cient kernel convolution mechanisms are used to evaluate entropy reduction for each sensor ray, and for each possible robot orientation, taking frontiers and obstacles into account. In the end, the computation of this ¿eld on the entire C-space is shown to be very efficient computationally. The approach is tested in simulations in a common publicly available dataset comparing favorably both in quality of estimates and execution time against another entropy reduction strategy that uses occupancy maps
CitacióVallve, J.; Andrade-Cetto, J. Mobile robot exploration with potential information fields. A: European Conference on Mobile Robots. "Proceedings of the 6th European Conference on Mobile Robots". Barcelona: 2013, p. 222-227.
Versió de l'editorhttp://dx.doi.org/10.1109/ECMR.2013.6698846
Fitxers | Descripció | Mida | Format | Visualitza |
---|---|---|---|---|
1439-Mobile-rob ... ial-information-fields.pdf | 502,5Kb | Visualitza/Obre |