Exploration using an information-based reaction-diffusion process

Publication Type:
Conference Proceeding
Citation:
Australasian Conference on Robotics and Automation, ACRA, 2013
Issue Date:
2013-01-01
Metrics:
Full metadata record
Files in This Item:
Filename Description Size
Thumbnail2013001458OK.pdf4.73 MB
Adobe PDF
In this paper, a novel solution for autonomous robotic exploration is proposed. We model the distribution of information in an unknown environment as an unsteady diffiusion process, which can be an appropriate mathematical for- mulation and analogy for expanding, time- varying, and dynamic environments. This in- formation distribution map is the solution of the diffusion process partial diffierential equa- tion, and is regressed from sensor data as a Gaussian Process. Optimization of the pro- cess parameters leads to an optimal frontier map which describes regions of interest for fur- ther exploration. Since the presented approach considers a continuous model of the environ- ment, it can be used to plan smooth exploration paths exploiting the structural dependencies of the environment whilst handling sparse sensor measurements. The performance of the ap- proach is evaluated through simulation results in the well-known Freiburg and Cave maps.
Please use this identifier to cite or link to this item: