Terrain assessment is a key aspect for autonomous exploration rovers, surrounding environment recognition is required for multiple purposes, such as optimal trajectory planning and autonomous target identification. In this work we present a technique to generate accurate three-dimensional semantic maps for Martian environment. The algorithm uses as input a stereo image acquired by a camera mounted on a rover. Firstly, images are labeled with DeepLabv3+, which is an encoder-decoder Convolutional Neural Networl (CNN). Then, the labels obtained by the semantic segmentation are combined to stereo depth-maps in a Voxel representation. We evaluate our approach on the ESA Katwijk Beach Planetary Rover Dataset.
@article{arxiv.2006.09761,
title = {Evaluation of 3D CNN Semantic Mapping for Rover Navigation},
author = {Sebastiano Chiodini and Luca Torresin and Marco Pertile and Stefano Debei},
journal= {arXiv preprint arXiv:2006.09761},
year = {2020}
}
Comments
To be presented at the 7th IEEE International Workshop on Metrology for Aerospace (MetroAerospace)