RL-Aided Cognitive ISAC: Robust Detection and Sensing-Communication Trade-offs

2025-11-04

AI Summary

To address radar sensing performance degradation in large-scale MIMO-ISAC systems under dynamic, unknown interference, this paper proposes a reinforcement learning (RL)-driven cognitive framework. The framework employs the SARSA algorithm to establish a model-free, adaptive online learning mechanism for real-time target localization, and integrates a Wald-type detector to handle non-Gaussian clutter. It further derives a closed-form waveform optimization solution that explicitly balances sensing and communication performance. Monte Carlo simulations demonstrate that, while maintaining downlink throughput, the proposed method significantly improves detection probability and simultaneously enhances spectral efficiency and interference robustness compared to orthogonal and non-learning adaptive baselines. The core contribution lies in the deep integration of model-free RL with joint waveform design—achieving, for the first time in ISAC systems, an analytically tractable, dynamic trade-off between sensing accuracy and communication performance.

Technology Category

• Search and Optimization: Learning to Search
• Machine Learning: Reinforcement Learning
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

This paper proposes a reinforcement learning (RL)-aided cognitive framework for massive MIMO-based integrated sensing and communication (ISAC) systems employing a uniform planar array (UPA). The focus is on enhancing radar sensing performance in environments with unknown and dynamic disturbance characteristics. A Wald-type detector is employed for robust target detection under non-Gaussian clutter, while a SARSA-based RL algorithm enables adaptive estimation of target positions without prior environmental knowledge. Based on the RL-derived sensing information, a joint waveform optimization strategy is formulated to balance radar sensing accuracy and downlink communication throughput. The resulting design provides an adaptive trade-off between detection performance and achievable sum rate through an analytically derived closed-form solution. Monte Carlo simulations demonstrate that the proposed cognitive ISAC framework achieves significantly improved detection probability compared to orthogonal and non-learning adaptive baselines, while maintaining competitive communication performance. These results underline the potential of RL-assisted sensing for robust and spectrum-efficient ISAC in next-generation wireless networks.

Problem

• Robust target detection under non-Gaussian clutter environments
• Adaptive estimation of target positions without environmental knowledge
• Balancing radar sensing accuracy with downlink communication throughput

Innovation

• Reinforcement learning optimizes sensing-communication trade-offs
• Wald-type detector enables robust detection in non-Gaussian clutter
• Joint waveform balancing sensing accuracy and communication throughput