Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Logic-Free Building Automation: Learning the Control of Room Facilities with Wall Switches and Ceiling Camera

Hideya Ochiai, Kohki Hashimoto, Takuya Sakamoto, Seiya Watanabe, Ryosuke Hara, Ryo Yagi, Yuji Aizono, Hiroshi Esaki

TL;DR

This work proposes a new architecture for logic-free building automation (LFBA) that leverages deep learning (DL) to control room facilities without predefined logic, allowing the DL model to learn users' preferred controls directly from the scenes and switch states.

Abstract

Artificial intelligence enables smarter control in building automation by its learning capability of users' preferences on facility control. Reinforcement learning (RL) was one of the approaches to this, but it has many challenges in real-world implementations. We propose a new architecture for logic-free building automation (LFBA) that leverages deep learning (DL) to control room facilities without predefined logic. Our approach differs from RL in that it uses wall switches as supervised signals and a ceiling camera to monitor the environment, allowing the DL model to learn users' preferred controls directly from the scenes and switch states. This LFBA system is tested by our testbed with various conditions and user activities. The results demonstrate the efficacy, achieving 93%-98% control accuracy with VGG, outperforming other DL models such as Vision Transformer and ResNet. This indicates that LFBA can achieve smarter and more user-friendly control by learning from the observable scenes and user interactions.

Logic-Free Building Automation: Learning the Control of Room Facilities with Wall Switches and Ceiling Camera

TL;DR

This work proposes a new architecture for logic-free building automation (LFBA) that leverages deep learning (DL) to control room facilities without predefined logic, allowing the DL model to learn users' preferred controls directly from the scenes and switch states.

Abstract

Artificial intelligence enables smarter control in building automation by its learning capability of users' preferences on facility control. Reinforcement learning (RL) was one of the approaches to this, but it has many challenges in real-world implementations. We propose a new architecture for logic-free building automation (LFBA) that leverages deep learning (DL) to control room facilities without predefined logic. Our approach differs from RL in that it uses wall switches as supervised signals and a ceiling camera to monitor the environment, allowing the DL model to learn users' preferred controls directly from the scenes and switch states. This LFBA system is tested by our testbed with various conditions and user activities. The results demonstrate the efficacy, achieving 93%-98% control accuracy with VGG, outperforming other DL models such as Vision Transformer and ResNet. This indicates that LFBA can achieve smarter and more user-friendly control by learning from the observable scenes and user interactions.
Paper Structure (10 sections, 3 figures, 2 tables)

This paper contains 10 sections, 3 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Logic-Free Building Automation with Deep Learning
  4. System Architecture
  5. Manual-Automation Switcher
  6. LFBA Testbed and Dataset
  7. Evaluation
  8. Experiment Setting
  9. Performance of Control Generation
  10. Conclusion

Figures (3)

  • Figure 1: Logic-Free Building Automation with Deep Learning. This architecture trains a DL model using the wall switch states and the scene obtained from the ceiling camera. In automation mode, the model directly controls the associated facilities.
  • Figure 2: The configuration of Logic-Free Building Automation Testbed at our institute. We have collected the dataset by shooting photos from a ceiling camera as Table \ref{['tab:dataset_profile']} with several lighting conditions and clothing.
  • Figure 3: Data collection runs by different clothes for diversity. Separation by runs allows effective 5-fold cross-run validation.