Localization of Camera-free Capsule Robot within the Gastrointestinal Tract
Bibliographic record
Abstract
Capsule robots have emerged as a promising tool for minimally invasive sampling of the gastrointestinal (GI) tract for early disease detection. However, effective localization of these capsule robots, especially the battery-free capsule robot without an on-board camera, within the GI tract remain challenging due to its complex, deformable geometry and limited accessibility. Accurate localization is essential for clinical deployment, for targeting disease site, and for improving the safety of the procedure. Compared with existing imaging techniques such as X-ray or CT, magnetic localization provides a radiation-free alternative for precise capsule robot localization. In this project, we designed a localization method for a magnetic battery-free capsule robot using a Hall effect sensor array, magnetic field superposition, and particle filtering. To enable localization, a robotic arm positions a permanent magnet (robotic arm magnet) with pre-calculated position and orientation. A magnetic capsule robot containing a magnetic compartment (capsule magnet) is placed within the setup mimicking the GI tract, and the Hall effect sensor array measures the combined field generated by both sources. By applying a magnetic field superposition model, supported and validated by finite element analysis of the generated magnetic field, the system can separate the capsule’s contribution (i.e., from capsule magnet) from the known actuator field (i.e., from robotic arm magnet). These refined measurements are then processed by a particle filter algorithm to calculate the capsule’s position in real-time. Future work will focus on tuning parameters used in the particle filter algorithm, expanding the sensor array to increase the workspace area, and implementing closed-loop force control to enable capsule navigation relying on the localization information.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".