This paper presents a novel approach for robust off-road navigation based on deep convolutional neural networks which are combined with OpenStreetMap data to perform a forest path-based local localization approach. Corresponding near features are used to integrate navigation relevant world knowledge into a local multi-feature map. A behavior-based controller adapts the robot’s trajectory based on available features and its detection quality. The approach was tested in the Rhineland-Palatinate forest. Different forest way detection setups were evaluated and are discussed in detail. Additionally, the autonomous mobile robot GatorX855D followed a forest trail using the resulting multi-feature map.
CITATION STYLE
Wolf, P., Vierling, A., Ropertz, T., Velden, S., Guzman, C., & Berns, K. (2022). Autonomous Off-Road Navigation Using Near-Feature-Based World Knowledge Incorporation on the Example of Forest Path Detection. In Lecture Notes in Networks and Systems (Vol. 412 LNNS, pp. 165–182). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-030-95892-3_13
Mendeley helps you to discover research relevant for your work.