loading page

Evaluation of Machine Learning Methodologies for Novelty-based Target Selection in Planetary Imaging Data Sets: Examples from the Mars Science Laboratory Mission
  • +4
  • Favour Nerrise,
  • Hannah Kerner,
  • Kiri Wagstaff,
  • Steven Lu,
  • Raymond Francis,
  • Umaa Rebbapragada,
  • James Bell
Favour Nerrise
University of Maryland, College Park

Corresponding Author:[email protected]

Author Profile
Hannah Kerner
University of Maryland College Park
Author Profile
Kiri Wagstaff
Jet Propulsion Laboratory, California Institute of Technology
Author Profile
Steven Lu
Jet Propulsion Laboratory
Author Profile
Raymond Francis
Jet Propulsion Laboratory, California Institute of Technology
Author Profile
Umaa Rebbapragada
NASA Jet Propulsion Laboratory
Author Profile
James Bell
Arizona State University
Author Profile


In-situ novelty-based target selection of scientifically interesting (“novel”) surface features can expedite follow-up observations and new discoveries for the Mars Science Laboratory (MSL) rover and other planetary exploration missions. This study aims to identify which methods perform best for detecting novel surface features in MSL Navcam images for follow-up observations with the ChemCam instrument, as a complement to the existing Autonomous Exploration for Gathering Increased Science (AEGIS) onboard targeting system. We created a dataset of 6630 candidate targets within Navcam grayscale images acquired between sols 1343-2578 using the Rockster algorithm. These were the same target candidates considered by AEGIS, chosen to enable direct comparison to past AEGIS target selections. We employed five novelty detection methods, namely Discovery via Eigenbasis Modeling of Uninteresting Data (DEMUD), Isolation Forest, Principal Component Analysis (PCA), Reed-Xiaoli (RX) detector, and Local RX. To evaluate the algorithm selections, a member of the MSL science operations team independently identified candidate targets that represented example scenarios of novel geology that we would desire an algorithm to identify, such as layered rocks, light-toned unusual textures, and small light-toned veins. We compared these methods to selections made by AEGIS and a random baseline. Initial experiments for three scenarios showed that Local RX most frequently prioritized novel targets, followed by DEMUD and AEGIS. Our next steps in this study include evaluating input feature representations other than pixel intensities (e.g., Histogram of Oriented Gradients features), performing additional experiments to evaluate novel target prioritization performance, and selecting target candidates in Mastcam color images.