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.
@inproceedings{cai2023buildsys,
author = {Cai, Weijia and Huang, Lei and Zou, Zhengbo},
title = {RoboAuditor: Goal-Oriented Robotic System for Assessing Energy-Intensive Indoor Appliance via Visual Language Models},
year = {2023},
isbn = {9798400702303},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3600100.3623739},
doi = {10.1145/3600100.3623739},
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.},
booktitle = {Proceedings of the 10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation},
pages = {130–139},
numpages = {10},
keywords = {deep learning, visual-language model, Energy auditing, robotics},
location = {Istanbul, Turkey},
series = {BuildSys '23}
}