Recovering the 3D UUV Position using UAV Imagery in Shallow-Water Environments
About
In this paper we propose a novel approach aimed at recovering the 3D position of an UUV from UAV imagery in shallow-water environments. Through combination of UAV and UUV measurements, we show that our method can be utilized as an accurate and cost-effective alternative when compared to acoustic sensing methods, typically required to obtain ground truth information in underwater localization problems. Furthermore, our approach allows for a seamless conversion to geo-referenced coordinates which can be utilized for navigation purposes. To validate our method, we present the results with data collected through a simulation environment and field experiments, demonstrating the ability to successfully recover the UUV position with sub-meter accuracy.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Multi-task Language Understanding | MMLU | MMLU Accuracy64.91 | 442 | |
| Commonsense Reasoning | HellaSwag | HellaSwag Score84.02 | 53 | |
| Science Question Answering | ARC-C | ARC-C Score60.54 | 43 | |
| Mathematical Reasoning | gsm | GSM Accuracy59.74 | 27 | |
| Truthfulness | TruthfulQA | TruthfulQA Score64.5 | 20 | |
| Code Generation | Codex | CodeX Score45.43 | 20 | |
| Aggregate performance evaluation | MMLU, GSM, HellaSwag, TruthfulQA, ARC-C, CodeX | Improvement3.15 | 18 |