Feasibility study of using the RoboEarth cloud engine for rapid mapping and tracking with small unmanned aerial systems
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. This paper presents the ongoing development of a small unmanned aerial mapping system (sUAMS) that in the future will track its trajectory and perform 3D mapping in near-real time. As both mapping and tracking algorithms require powerful computational capabilities and large data storage facilities, we propose to use the RoboEarth Cloud Engine (RCE) to offload heavy computation and store data to secure computing environments in the cloud. While the RCE's capabilities have been demonstrated with terrestrial robots in indoor environments, this paper explores the feasibility of using the RCE in mapping and tracking applications in outdoor environments by small UAMS. The experiments presented in this work assess the data processing strategies and evaluate the attainable tracking and mapping accuracies using the data obtained by the sUAMS. Testing was performed with an Aeryon Scout quadcopter. It flew over York University, up to approximately 40 metres above the ground. The quadcopter was equipped with a single-frequency GPS receiver providing positioning to about 3 meter accuracies, an AHRS (Attitude and Heading Reference System) estimating the attitude to about 3 degrees, and an FPV (First Person Viewing) camera. Video images captured from the onboard camera were processed using VisualSFM and SURE, which are being reformed as an Application-as-a-Service via the RCE. The 3D virtual building model of York University was used as a known environment to georeference the point cloud generated from the sUAMS' sensor data. The estimated position and orientation parameters of the video camera show increases in accuracy when compared to the sUAMS' autopilot solution, derived from the onboard GPS and AHRS. The paper presents the proposed approach and the results, along with their accuracies.
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 | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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