🤖 AI Summary
This work addresses the challenge of achieving low-complexity, high-order modulation-compatible MIMO detection with reliable soft-output generation in resource-constrained edge scenarios such as 5G RedCap and IoT. The paper proposes recurSIC, a lightweight learning-based MIMO detection framework inspired by successive interference cancellation (SIC). By integrating a tunable-complexity, multi-path hypothesis tracking mechanism within a single forward pass, recurSIC efficiently produces high-quality soft information. The approach embeds a compact neural network into the SIC architecture, requiring only a minimal number of parameters to simultaneously deliver accurate hard decisions and reliable soft outputs. Experimental results demonstrate that recurSIC achieves near-optimal detection performance under real-world wireless channels while significantly reducing computational overhead, making it well-suited for deployment in edge MIMO receivers.
📝 Abstract
Low-complexity multiple-input multiple-output (MIMO) detection remains a key challenge in modern wireless systems, particularly for 5G reduced capability (RedCap) and internet-of-things (IoT) devices. In this context, the growing interest in deploying machine learning on edge devices must be balanced against stringent constraints on computational complexity and memory while supporting high-order modulation. Beyond accurate hard detection, reliable soft information is equally critical, as modern receivers rely on soft-input channel decoding, imposing additional requirements on the detector design. In this work, we propose recurSIC, a lightweight learning-based MIMO detection framework that is structurally inspired by successive interference cancellation (SIC) and incorporates learned processing stages. It generates reliable soft information via multi-path hypothesis tracking with a tunable complexity parameter while requiring only a single forward pass and a minimal parameter count. Numerical results in realistic wireless scenarios show that recurSIC achieves strong hard- and soft-detection performance at very low complexity, making it well suited for edge-constrained MIMO receivers.