Gesture-Aware Indoor THz ISAC Systems for Adaptive Resource Allocation

Researchers have proposed new frameworks for indoor integrated sensing and communication (ISAC) and integrated sensing, communication, and computing (ISCC) systems, enhancing adaptive resource allocation and gesture recognition.

A multi-user indoor THz ISAC system has been designed to adapt communication based on gesture recognition, using an extended Kalman filter to track gesture variations^[1]. The access point dynamically adjusts resource allocation in response to detected changes, maximizing the overall sensing signal-to-interference-plus-noise ratio (SINR) through an adaptive joint optimization algorithm. Simulation results show superior sensing accuracy and communication performance compared to conventional single-variable optimization methods. Meanwhile, a Cramer-Rao bound (CRB)-guided framework has been proposed for indoor mmWave ISCC systems to minimize human pose prediction error under various constraints^[2]. This framework uses CRB to guide resource allocation and characterize sensing power's impact on range-estimation uncertainty. An adaptive-depth Mamba-based pose prediction model captures the impact of computation resources on prediction performance, and an alternating optimization (AO)-based algorithm efficiently solves the joint resource allocation problem.