Planetary Exploration With Robot Teams: Implementing Higher Autonomy With Swarm Intelligence
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
Since the beginning of space exploration, Mars and the moon have been examined via orbiters, landers, and rovers. More than 40 missions have targeted Mars, and over 100 have been sent to the moon. Space agencies continue to focus on developing novel strategies and technologies for probing celestial bodies. Multirobot systems are particularly promising for planetary exploration, as they are more robust to individual failure and have the potential to examine larger areas; however, there are limits to how many robots an operator can control individually. We recently took part in the European Space Agency's (ESA's) interdisciplinary equipment test campaign (PANGAEA-X) at a lunar/Mars analog site in Lanzarote, Spain. We used a heterogeneous fleet of unmanned aerial vehicles (UAVs)-a swarm-to study the interplay of systems operations and human factors. Human operators directed the swarm via ad hoc networks and data-sharing protocols to explore unknown areas under two control modes: in one, the operator instructed each robot separately; in the other, the operator provided general guidance to the swarm, which self-organized via a combination of distributed decision making and consensus building. We assessed cognitive load via pupillometry for each condition and perceived task demand and intuitiveness via selfreport. Our results show that implementing higher autonomy with swarm intelligence can reduce workload, freeing the operator for other tasks such as overseeing strategy and communication. Future work will further leverage advances in swarm intelligence for exploration missions.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.002 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.001 |
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