Semantic communication and sensing combined in one adjustable waveform
Adaptive Pilot Selection for Unified Semantic Communication and Semantic Sensing in ISAC
Artificial Intelligence
Summary
Wireless networks need to send information and sense the environment at the same time. The authors created a new system called SemISAC that uses one signal to both communicate semantic details like road images and sense nearby objects. Their system adjusts parts of the signal used for communication or sensing depending on conditions. Tests in a vehicle setting showed SemISAC accurately understands road scenes and identifies objects better than older methods. It combines both tasks efficiently using smart AI on both sender and receiver sides.
What this means in practice
- •For vehicular communication engineers: Design vehicle-to-vehicle systems that share detailed road scene understanding while simultaneously sensing surrounding objects using a single adaptable signal.
- •For wireless system developers: Build integrated communication and sensing networks that dynamically adjust signal pilots to optimize both data transmission and environmental sensing accuracy under varying channel conditions.
Authors
Muhammad Abubakar Rashid, Muhammad Hannan Akram, Haejoon Jung, Syed Ali Hassan
Abstract
Semantic communication (SemCom) and integrated sensing and communication (ISAC) are promising technologies for future 6G wireless networks. Existing studies have applied semantic technology to either the communication module or the sensing module of ISAC. In this work, we propose SemISAC, which performs both SemCom and semantic sensing within a single dual-function waveform. SemISAC uses a joint semantic encoder that extracts task-specific information for both communication and sensing. We evaluate SemISAC in a vehicular scenario in which vehicles share pixel-wise segmentation of the road environment and, through sensing, classify surrounding objects and estimate their ranges. On the transmitter side, a deep learning encoder converts the input road-scene image into semantic symbols and places them on the data cells of an OFDM grid, while the remaining cells serve as pilots for channel state information estimation and sensing. The pilot configuration is adaptively optimized based on the channel conditions to balance communication and sensing requirements. At the receiver, a deep learning model reconstructs the segmentation from the received waveform, while the transmitting vehicle captures the reflected waveforms from surrounding objects and uses task-specific deep learning decoders for target recognition and range estimation. Simulation results show that SemISAC achieves a segmentation accuracy close to that of the dedicated SemCom module while outperforming both conventional and semantic baselines in target recognition and range estimation.