Towards Planetary Drilling Autonomy using Subsurface Fault and Anomaly Detection

Sarah Boelter, Greta Brown, Thomas Stucky, Rene Mai, Ebasa Temesgen, Lucas Weber, Brian Glass, Maria Gini

Keywords: Field Robotics, Planetary Drilling, Subsurface State Estimation, Fault Detection, Space Robotics

TL;DR: Methods to make planetary drills more aware of their subsurface environment to better enable future drilling autonomy, tested in a lab, the Canadian Arctic, and Antarctica.

Abstract: In extraterrestrial planetary environments, environmental, computing, energy, and operational constraints require robotic agents to complete tasks without human supervision. Specialized extraterrestrial robotic drilling agents currently lack autonomous drilling capabilities, primarily because research into subsurface environment for autonomous drilling remains in its early stages. We validate work using online model-free time-series subspace analysis methods for noisy and sparse data to estimate drilling faults from drill avionics telemetry in Haughton Crater in the Canadian High Arctic. We introduce a multivariate subsurface anomaly detection method that leverages sensor fusion of avionics telemetry evaluated at Mars planetary analog sites in Antarctica. We also outline planned fieldwork in summer 2026 at Barringer Crater.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 3