Active Sensing for RIS-Aided Tracking and Power Control: A Hybrid Neuroevolution and Supervised Learning Approach

2026-06-30

AI Summary

This work addresses the challenge of energy-efficient tracking for power-constrained mobile users in reconfigurable intelligent surface (RIS)-assisted systems. To this end, the authors propose a dual-agent deep learning framework that integrates neuroevolution with supervised learning to jointly optimize the discrete RIS phase shifts and user transmit power, enabling low-overhead, real-time active sensing under one-bit limited feedback. Notably, this approach pioneers the application of neuroevolution to RIS phase control, effectively circumventing the non-differentiability of discrete phases and the bottleneck of minimal feedback, while remaining compatible with both single- and multi-antenna base station architectures. Experimental results demonstrate that the proposed method achieves robust, high-accuracy tracking across diverse mobility models, significantly outperforming extended Kalman filters, particle filters, and existing machine learning baselines, and also substantially surpassing conventional fingerprinting, deep reinforcement learning, and backpropagation-based estimators in static localization scenarios.

Abstract

This paper studies energy efficient tracking of power-limited mobile users with the assistance of a Reconfigurable Intelligent Surface (RIS). Since localization pilot transmissions dominate the energy budget of power-constrained devices, we introduce a low-overhead feedback link from the Base Station (BS) to the user to enable dynamic uplink power control. To navigate the discrete and decentralized nature of this active sensing problem, we propose a novel Dual-Agent (DA) deep learning framework that jointly optimizes the discrete RIS phase profiles and the UE's transmit power in real time. Specifically, our approach employs a hybrid training methodology integrating the neuroevolution paradigm with supervised learning, effectively overcoming the non-differentiability of discrete phase responses from the RIS unit elements and the strict information bottleneck of single-bit feedback messages for pilot power control. The proposed DA active sensing framework can be applied with both single- and multi-antenna BSs, the latter with only minor modifications in the structure of one NN: an additional output branch with appropriate structure is included for the latter case to select a valid digital combiner from a finite set. Extensive numerical simulations demonstrate that the proposed scheme achieves highly accurate and robust tracking across diverse target motion models, outperforming extended Kalman and particle filters, as well as, machine learning-based trackers. Furthermore, in static localization, it is shown to significantly outperform traditional fingerprinting schemes, deep reinforcement learning baselines, and standard backpropagation-based estimators.

Problem

• Reconfigurable Intelligent Surface
• active sensing
• energy-efficient tracking
• power control
• mobile user localization

Innovation

• Reconfigurable Intelligent Surface
• Active Sensing
• Neuroevolution
• Hybrid Learning
• Power Control