This article is reprinted from Xinhua News Agency;
Xinhua News Agency, Tianjin, December 10th (reporters Zhang Jianxin, Li Yating) On the 10th, the Tianjin University news office reported that the Tianjin University network and cloud computing team has made a key breakthrough in the field of wireless sensing. They have turned the ordinary Wi-Fi signals at home into a "perception manager" in the home environment. By analyzing changes in human activity through Wi-Fi signals, it can determine people's needs without voice commands, allowing smart homes to provide corresponding services. The related research results have been published in the international journal IMWUT.
According to the team, currently, most smart homes still rely on users issuing instructions or specific sensors, making it difficult to achieve an imperceptible and continuous understanding of users' real-time changing states and needs. In response, the research team developed a new high-precision perception application. It does not require users to wear any devices, and by analyzing the subtle changes in Wi-Fi signals caused by human activities, it can perceive a person's location, state, and behavior, and command smart home devices to provide corresponding services.
However, to bring the high-precision perception application from the laboratory into real homes, two major practical bottlenecks must be solved: first, the system deployment is complicated, usually requiring professional personnel to repeatedly debug and calibrate the positions of smart devices; second, signal blockage and reflection are severe in complex home environments, leading to inaccurate perception.
To address the issue of "difficult deployment," the team innovatively turned its attention to the increasingly popular robot vacuum cleaners in homes, transforming them into "automatic data collectors." During its daily cleaning and mapping process, the system can simultaneously automatically build a physical space map and a Wi-Fi signal map of the home, and accurately identify and record the positions of routers, smart speakers, and other devices with a precision of 0.1 meters. Users just need to let the robot vacuum cleaner clean normally once, and the system initialization can be completed, completely eliminating the hassle of professional installation and manual measurement.
Diagram showing the use of a robot vacuum cleaner for automatic calibration of home device positions. Xinhua News Agency photo.
To address the issue of "low accuracy," the team abandoned the idealized assumption of unobstructed signals in traditional models and built a new theoretical model for the real family environment full of items. This model can "understand" the propagation rules of Wi-Fi signals in complex environments, achieving stable and reliable high-precision perception in real homes.
The research results were completed under the guidance of Associate Professor Tong Xinyu and Professor Li Keqiu from the School of Computer Science and Technology, and Assistant Researcher Chen Sheng from the School of Cybersecurity at Tianjin University. Doctoral candidates Tan Renrui and Meng Xuani are the first authors respectively.
Tong Xinyu said that the research results have cleared key obstacles for wireless sensing technology to reach thousands of households, and also provided core technical support for building a more intelligent and considerate living environment in the future.
Original article: toutiao.com/article/7582240808222147082/
Statement: This article represents the views of the author.