[IEEE ComSoc-SPS ISAC Webinar] 3rd Prof.Visa Koivunen and Prof. Ahmed Alkhateeb

Webinar 1: Prof. Visa Koivunen (50min Talk + 10 Q&A)
Title: Signal Processing, Reinforcement Learning and Waveform Optimization for Multicarrier Joint Radar-Communication Systems

Abstract:
Joint radar–communications (JRC) systems integrate radio frequency sensing and communications. They operate in a shared and congested, possibly even contested–spectrum with the goal of improving both communications and radar performances. We are considering JRC systems that cooperate or are co-designed for mutual benefits. Co-designed systems may share waveforms, hardware, and antenna resources. Moreover, awareness about channel state and interference is typically exchanged. The JRC systems have a number of degrees of freedom (DoF) and operational parameters that can be selected or adjusted to optimize their performance either by using structured optimization or machine learning. Examples of such parameters are frequency band, beampatterns, antenna selection, the modulation method, precoder–decoder designs, and power allocation. We focus on multicarrier waveforms used by most current and emerging wireless communication systems. Similarly, multicarrier waveforms have been employed for radar purposes. Radars have a variety of tasks such as target detection, tracking, parameter estimation and recognition with different objectives. We will present waveform optimization, reinforcement learning, interference management and signal processing methods for co-designed JRC systems that share channel and interference awareness. Model-based reinforcement learning approach is taken to exploit the rich structural knowledge of man-made communication and sensing systems and radio wave propagation. Optimizing operational parameters is modeled either as a radar-centric or communications-centric constrained optimization problem where the minimum desired performance levels for other sub-systems impose the constraints. The developed OFDM radar algorithms can take advantage of nonidealities such as carrier offsets and phase noise that are commonly considered an impairment in wireless communications. We demonstrate the achieved performance gains in different sensing and communication tasks and interference management through extensive simulation and analytical results.

Webinar 2: Prof. Ahmed Alkhateeb (50min Talk + 10 Q&A)
Title: Multi-Modal Sensing Aided Communications and the Role of Machine Learning

Abstract:
Wireless communication systems are moving to higher frequency bands (mmWave in 5G and above 100GHz in 6G and beyond) and deploying large antenna arrays at the infrastructure and mobile users (massive MIMO, mmWave/terahertz MIMO, reconfigurable intelligent surfaces, etc.). While using large antenna arrays and migrating to higher frequency bands enable satisfying the increasing demand in data rate, they also introduce new challenges that make it hard for these systems to support mobility and maintain high reliability and low latency. In this talk, I will first motivate the use of sensory data and machine learning to address these challenges. Then, I will present DeepSense 6G, the world's first large-scale real-world multi-modal sensing and communication dataset that enables the research in a wide range of integrated sensing and communication applications. After that, I will go over a few machine learning tasks enabled by the dataset such as radar, LiDAR, camera, and position aided beam and blockage prediction. Finally, I will discuss some future research directions in the interplay of communications, sensing, and positioning.