RoboAuditor: Goal-Oriented Robotic System for Assessing Energy-intensive Indoor Appliance via Visual Language Models
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
Energy auditing is a crucial step in building retrofitting to enhance building energy efficiency. However, auditing tasks, such as profiling energy-consuming appliances in buildings, rely heavily on human inspectors, resulting in a time- and capital-intensive process. To this end, we propose an autonomous robotic system, dubbed RoboAuditor, for identifying and localizing energy-intensive appliances in buildings given text queries from humans. RoboAuditor utilizes visual language models to predict relevance scores between text queries and observed images for goal selection in robot navigation. It then automatically identifies and localizes queried appliances while self-navigating with efficient navigational strategies. For evaluation, we deploy the proposed robotic system on a wheeled robot equipped with an RGB-D camera and run auditing tests in 12 residential buildings in 3D simulation. These buildings exhibit diverse room counts, appliance quantities, and navigable areas, and they all feature energy-intensive appliances, such as air conditioners, heaters, dishwashers, and refrigerators. We conduct two groups of experiments: the first group uses the relevance score, and the second serves as a control group without the relevance score. Results demonstrate that RoboAuditor detects queried appliances and accurately localizes their positions in buildings with an average success rate of 68.05%, showing a significant margin of 6.8% higher than the control group.
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 | 0.000 |
| 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 it