Focus Bug: Learning Environmental Awareness for Efficient Mapless Navigation
Bibliographic record
Abstract
Tiny robots such as nano quadcopters or micro rovers are highly beneficial for various applications as they are inexpensive, agile, and safe for humans. However, their extreme size, weight, and power (SWAP) constraints lead to extremely limited compute, making autonomous navigation challenging. Existing approaches have enabled navigation within these tight constraints, but struggle in dynamic and cluttered scenes.To this end, we present Focus Bug, a novel and robust mapless navigation algorithm that can run on extremely limited hardware. Focus Bug reduces the amount of processed sensory data using a tiny reinforcement learning policy, only processing the inputs necessary for navigation. We use deep reinforcement learning (DRL) to identify critical parts of the robot’s range data and combine it with classical mapless navigation methods to benefit from their robustness and established performance. We implement and evaluate Focus Bug both on a drone in simulation and a micro-rover in the real world to show it can be applied across embodiments. Our hybrid approach outperforms the state-of-the-art in DRL navigation (57% less collisions in dynamic environments) while reducing the amount of range data processed by 87%, and achieving a 2.6X improvement in processing time compared to classical methods. Focus bug is the first method to achieve the high success rate of robust methods (97%) within such a tight compute budget.
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 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 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".