Wireless AI, made possible by 5G, makes new system efficiencies and user experiences possible, and also lays the foundation for future innovations.
Both artificial intelligence and 5G Advance are making inroads into digital networks, and out of the convergence comes wireless AI. The possibilities wireless AI brings are vast, from more intelligent enterprises to improved wireless systems themselves.
“AI can optimize device experiences with more efficient beam management and channel feedback computation, as well as enhanced capabilities like positioning and RF sensing,” says Taesang Yoo, senior director of technology for Qualcomm, in a recent blog post.
“Today, 5G is propelling the rapid proliferation of intelligent devices and services, with more than 1.5 billion connections globally,” he explains. “The rise of AI not only transforms our mobile experiences, such as improved camera quality or predictive texting, but also brings a unique opportunity to revolutionize the future of wireless communications.”
The future of AI is “hybrid,” Yoo continues, noting that splitting AI applications between central clouds and edge devices can make for the most efficient use of resources.
See also: 5G IoT Connections To Surpass 100 Million By 2026
The key to wireless AI is the emerging 5G Advanced standard, first unveiled by the 3GPP standards group in late 2021. “Wireless AI capabilities not only make new system efficiencies and user experiences possible, but also lay the foundation for future wireless AI innovations,” Yoo says.
Yoo’s team recently demonstrated a series wireless AI projects, including Intelligent industrial positioning that enables “centimeter-level accuracy in an indoor industrial IoT testbed.” In addition, wireless AI provides greater stability in network communications, and can manage multi-vendor systems and protocols.
In the not-too-distant future, the 6G network standard will pave the way to even more powerful wireless AI. “Our vision is for 6G to be an AI-native innovation platform,” says Yoo. “6G is expected to have a data-driven design that distributes AI throughout all protocols and layers, allowing it to continuously improve as more data is collected.”
