Target Localization from 3D data for On-Orbit Autonomous Rendezvous & Docking
Bibliographic record
Abstract
Neptec has developed a vision system for autonomous on-orbit rendezvous and docking that does not require the use of cooperative markers on the target spacecraft. The system uses an active TriDAR 3D sensor and efficient model based tracking algorithms to provide 6 degree of freedom (6DOF) relative pose information in real-time. The TriDAR (triangulation + LIDAR) sensing technology combines triangulation and Time-of-Flight (ToF) active ranging techniques within the same optical path. This configuration takes advantage of the complementary nature of these two imaging technologies and allows the system to provide fast and accurate 3 dimensional data at both short and long range. In partnership with the Canadian Space Agency (CSA), Neptec has developed a novel object localization algorithm that calculates the relative pose of a target spacecraft without requiring an initial estimate of the pose. This algorithm will be used to automatically initiate the model based tracking process and recover if tracking is lost. The technique was specifically designed for real-time operations in space where a target spacecraft could be tumbling and processing power is limited. Most traditional approaches to object recognition and pose estimation algorithms require high resolution data arranged in a grid such that convolution based operators can be used. This generally means that data acquisition is slow and real-time data processing requires a powerful computer. Neptec's approach follows the More Information Less Data (MILD) paradigm. It requires only a unorganized sparse 3D point cloud of the target, keeping the data acquisition time to a minimum.
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 0.003 |
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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".