Demo: Context-Model Generation for Safe Autonomous Transport Vehicles

BIB
Kuka, Christian and Gerwinn, Sebastian and Schweigert, Sören and Eilers, Sönke and Nicklas, Daniela
Proceedings of the 6th ACM International Conference on Distributed Event-Based Systems
Autonomously operating vehicles highly depend on the qual-ity of its sensors as they have to be aware of its surround-ings to react appropriately. Currently operating automatedguided vehicles cover only a limited area with their sensorsand therefore can only drive at low speeds. However, asmore and more sensors are available, it is essential to builda context-model, which fuses information of different sen-sors to cover a larger area and allow for an increased levelof autonomy. In this paper, we present a context-modelbased on a Bayesian occupancy filter which can be queriedvia a data stream management system in order to providethe necessary information at any point in time. Addition-ally, the Bayesian filter is pessimistically as it is constructedsuch that probability of occupancy is always upper bounded,to ensure a sufficient level of safety.
07 / 2012
978-1-4503-1315-5
inproceedings
ACM
DEBS '12
365-366
SaLsA
Sichere autonome Logistik- und Transportfahrzeuge im Außenbereich