Autonomous Navigation Performance Using Natural Feature Tracking during the OSIRIS-REx Touch-and-Go Sample Collection Event
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Abstract When the Origins, Spectral Interpretation, Resource Identification, and Security–Regolith Explorer (OSIRIS-REx) spacecraft collected a sample of surface material from asteroid Bennu in 2020 October, it was the first time that an autonomous optical navigation system relying on natural terrain features had been used to guide a spacecraft to a planetary surface. This system, called Natural Feature Tracking (NFT), works by rendering features from digital terrain models and then correlating them with the terrain in real-time navigation images to estimate the spacecraft's position and velocity with respect to the asteroid. Here we describe how the OSIRIS-REx mission built the catalog of features for NFT and how those features performed during rehearsals for and execution of the Touch-and-Go (TAG) sample collection event. Feature performance (quality and accuracy of match) in the rendering and correlation process is the basis of the NFT measurement. All features scored well above the minimum correlation threshold thanks to the effort invested in selecting and modeling them. Residuals across the TAG trajectory were small, indicating that features in the catalog were defined consistently relative to each other. NFT delivered the spacecraft to within 1 m of the targeted location, with a difference of only 3.5 cm and 1.4 s from the predicted location and time of touch. This exceptional performance was crucial for spacecraft safety given Bennu's rough and hazardous terrain.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.007 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it