arXiv:2606.14776v1 Announce Type: cross Abstract: Accurate position estimation is crucial for the successful implementation of future lunar landings using autonomous vehicles, especially in dangerous environments with sparse terrain features. In this paper, we propose a terrain relative navigation (TRN) algorithm combining our deep-learning crater detector, which was designed specifically for the NASA Crater Detection Challenge problem, and an Extended Kalman Filter (EKF). Our detector analyzes crater features from the monocular images acquired from orbit, and their matches with craters from a
The increasing push for autonomous lunar missions and the development of advanced AI techniques are converging to address critical navigation challenges in extraterrestrial environments.
Accurate and autonomous navigation is a cornerstone for successful, cost-effective, and safe lunar exploration and resource utilization, reducing reliance on human intervention for complex maneuvers.
Future lunar landers can achieve higher precision and autonomy in challenging terrains by integrating deep learning for crater detection with advanced filtering techniques, enabling more ambitious mission profiles.
- · Space agencies (NASA, ESA, CNSA)
- · Aerospace & Defense contractors
- · AI/ML companies specializing in computer vision
- · Lunar resource extraction companies
- · Traditional, less automated navigation systems
- · Missions overly reliant on earth-based telemetry for fine-tuned maneuvers
Improved success rates for autonomous lunar landings.
Accelerated development of lunar infrastructure and resource exploitation due to enhanced navigational capabilities.
Potential for establishing permanent human presence or robotic outposts on the Moon becomes more feasible without constant human oversight for complex operations.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG