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
Cooperation between an unmanned aerial vehicle (UAV) and unmanned surface vehicle (USV) can be critical in fields like search and rescue, marine ecology, and surveying. This is because, by landing a UAV on a USV for recharging, the agents can collaborate to eliminate their individual limitations; UAVs typically have a superior speed and vantage point compared to USVs, but can only remain airborne for short periods of time due to battery limitations, whereas USVs lack mobility and height but can remain at sea for extended periods of time and carry large batteries. The question our work this summer sought to answer is: how can we get a UAV-USV pair to seek out ”calm waters” and attempt a landing when and where the waves are most favorable? Due to the high risk associated with testing such a system on a real body of water, we developed a novel testbed that utilizes an unmanned ground vehicle (UGV) fitted with a custom-made 2-axis tilting landing pad that can pitch and roll to simulate the motion of a USV in a variety of wave conditions. We used this novel testbed with an indoor Crazyflie UAV to experimentally prove a cooperative model-predictive control (MPC) scheme. In essence, MPC works by optimizing control inputs using a model that encodes the dynamics of a system to pick the best series of control inputs from a finite set of valid inputs. Our work successfully proved the viability of a system where two agents use MPC to optimize their relative positions and the intensity of nearby waves to reach consensus on where and when to land. By landing 100+ times using a variety of system configurations, we were able to demonstrate a significantly increased likelihood of successful landings when using our control scheme.
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 | 0.003 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.004 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.002 |
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