Uncertainty Estimation for Planetary Robotic Terrain Segmentation

Marcus G. Müller, Maximilian Durner, Wout Boerdijk, Hermann Blum, Abel Gawel, Wolfgang Stürzl, Roland Siegwart, Rudolph Triebel

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


Terrain Segmentation information is crucial input for current and future planetary robotic missions. Labeling training data for terrain segmentation is a difficult task and can often cause semantic ambiguity. As a result, large portion of an image usually remains unlabeled. Therefore, it is difficult to evaluate network performance on such regions. Worse is the problem of using such a network for inference, since the quality of predictions cannot be guaranteed if trained with a standard semantic segmentation network. This can be very dangerous for real autonomous robotic missions since the network could predict any of the classes in a particular region, and the robot does not know how much of the prediction to trust. To overcome this issue, we investigate the benefits of uncertainty estimation for terrain segmentation. Knowing how certain the network is about its prediction is an important element for a robust autonomous navigation. In this paper, we present neural networks, which not only give a terrain segmentation prediction, but also an uncertainty estimation. We compare the different methods on the publicly released real world Mars data from the MSL mission.

Original languageEnglish
Title of host publication2023 IEEE Aerospace Conference, AERO 2023
PublisherIEEE Computer Society
ISBN (Electronic)9781665490320
StatePublished - 2023
Externally publishedYes
Event2023 IEEE Aerospace Conference, AERO 2023 - Big Sky, United States
Duration: 4 Mar 202311 Mar 2023

Publication series

NameIEEE Aerospace Conference Proceedings
ISSN (Print)1095-323X


Conference2023 IEEE Aerospace Conference, AERO 2023
Country/TerritoryUnited States
CityBig Sky


Dive into the research topics of 'Uncertainty Estimation for Planetary Robotic Terrain Segmentation'. Together they form a unique fingerprint.

Cite this