Edge Perception: Intelligent Wireless Sensing at Network Edge

TL;DR

This article discusses the interplay between edge AI and wireless sensing in edge perception, and presents various key techniques for two paradigms, namely edge AI empowered sensing and task-oriented sensing for edge AI, respectively.

Abstract

Future sixth-generation (6G) networks are envisioned to support intelligent applications across various vertical scenarios, which have stringent requirements on high-precision sensing as well as ultra-low-latency data processing and decision making. Towards this end, a new paradigm of edge perception networks emerges, which integrates wireless sensing, communication, computation, and artificial intelligence (AI) capabilities at network edge for intelligent sensing and data processing. This article provides a timely overview on this emerging topic. We commence by discussing wireless edge perception, including physical layer transceiver design, network-wise cooperation, and application-specific data analytics, for which the prospects and challenges are emphasized. Next, we discuss the interplay between edge AI and wireless sensing in edge perception, and present various key techniques for two paradigms, namely edge AI empowered sensing and task-oriented sensing for edge AI, respectively. Finally, we emphasize interesting research directions on edge perception to motivate future works.

Figures (4)

• Figure 1: Illustration of applications in edge perception.
• Figure 2: Illustration of a pipeline of the edge perception procedure.
• Figure 3: Illustration of the interplay between edge AI and wireless sensing.
• Figure 4: Illustration of edge AI network.