Autonomous humanoid robot navigation using augmented reality technique
Bibliographic record
Abstract
This work presents a novel vision-based navigation strategy for autonomous humanoid robots using augmented reality (AR). In the first stage, a platform is developed for indoor and outdoor human location positioning and navigation using mobile augmented reality. The image sequence would be obtained by a smart phone's camera and the location information will be provided to the user in the form of 3D graphics and audio effects containing location information. To recognize a location, an image database and location model is pre-constructed to relate the detected AR-marker's position to the map of environment. The AR-markers basically act as active landmarks placed in undiscovered environments, sending out location information once detected by a camera. The second stage implements the same algorithm on an autonomous humanoid robot to be used as its navigation module. This is achieved by coupling the robot odometry and inertial sensing with the visual marker detection module. Using this system, the robot employs its vision system to enhance its localization robustness and allow quick recovery in lost situations by detecting the active landmarks or the so called AR-markers. The problem of motion blur resulting from the 6-DOF motion of humanoid's camera is solved using an adaptive thresholding technique developed to increase the robustness of the augmented reality marker detection under different illumination conditions and camera movements. For our experiments, we used the humanoid robot NAO and verified the performance of this navigation methodology in real-world scenarios.
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 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 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 | 0.000 | 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".