arXiv subjects

Shuangshuang Li

Publications and source records attributed to Shuangshuang Li.

4 recordsLinked to original sources

arXiv2026

Sensing-Aided Channel Estimation for Near-Field MIMO ISAC Systems via Cross-Attention Transformer

Near-field integrated sensing and communication (ISAC) can deliver the high spatial resolution and transmission capability with the shared spectrum and hardware. Due to the partial overlap between communication scatterers and radar targets, the sensing information can provide valuable priors to enhance the channel estimation while fusing the two heterogeneous modalities remain challenging. To address this problem, a Cross-Attention Transformer based Channel Estimation Neural Network (CAT-CENet) is developed, which includes a communication pilot branch generating the the Key and Value features and a sensing information branch generating the Query feature. By elaborating the three-module structure, CAT-CENet can focus on features of overlapped targets automatically without need of identifying them in advance. The modality contribution is theoretically analyzed based on the Shapley value to verify the cross-attention gain achieved by CAT-CENet. Simulation results show that CAT-CENet outperforms the state-of-the-art schemes, especially with the higher overlapping proportion, and is robust to the model pruning.

eess.SP↗

arXiv2026

Improving Robotic Imitation Learning via Trajectory Standardization

Imitation learning for robotic manipulation relies on large sets of human demonstration trajectories, which are often noisy and temporally irregular due to variable operator speed, intermittent pauses, and inconsistent action density. A common preprocessing strategy is time-uniform downsampling to shorten sequences, but it cannot effectively remove speed-induced non-uniformity or redundant pauses. This mismatch degrades data quality and hinders policy learning. To address this issue, we propose Information-Standardized Trajectory Resampling (ISR), an offline preprocessing method for effective imitation learning. ISR resamples each trajectory by enforcing approximately equal information distance between adjacent points. Specifically, we map trajectories onto an information-modulated Riemannian manifold and perform geodesic-equidistant parameterization. We construct an information-intensity field from velocity and acceleration norms: the velocity term removes small-motion redundancy, while the acceleration term preserves high-curvature and fine-manipulation phases. We evaluate ISR on three real-world manipulation tasks with mainstream imitation learning policies. Compared with the baseline time-uniform 3x downsampling, ISR improves task success rates by about 25%, remains robust across datasets collected from different operators, and reduces both dataset size and training cost. The code and videos are publicly available at https://d-robotics-ai-lab.github.io/isr.page.

cs.RO↗

arXiv2025

LLM4XCE: Large Language Models for Extremely Large-Scale Massive MIMO Channel Estimation

Extremely large-scale massive multiple-input multiple-output (XL-MIMO) is a key enabler for sixth-generation (6G) networks, offering massive spatial degrees of freedom. Despite these advantages, the coexistence of near-field and far-field effects in hybrid-field channels presents significant challenges for accurate estimation, where traditional methods often struggle to generalize effectively. In recent years, large language models (LLMs) have achieved impressive performance on downstream tasks via fine-tuning, aligning with the semantic communication shift toward task-oriented understanding over bit-level accuracy. Motivated by this, we propose Large Language Models for XL-MIMO Channel Estimation (LLM4XCE), a novel channel estimation framework that leverages the semantic modeling capabilities of large language models to recover essential spatial-channel representations for downstream tasks. The model integrates a carefully designed embedding module with Parallel Feature-Spatial Attention, enabling deep fusion of pilot features and spatial structures to construct a semantically rich representation for LLM input. By fine-tuning only the top two Transformer layers, our method effectively captures latent dependencies in the pilot data while ensuring high training efficiency. Extensive simulations demonstrate that LLM4XCE significantly outperforms existing state-of-the-art methods under hybrid-field conditions, achieving superior estimation accuracy and generalization performance.

cs.LG↗

arXiv2025

Lamb wave-based MVDR imaging and CNN classification of defects in pipelines

Significant progress has been made in ultrasonic guided wave (UGW) technology for pipe signal processing and defect imaging recently. However, developing a defect localization and imaging algorithm that requires fewer parameters, offers a wide imaging range, and achieves high positioning accuracy remains a considerable challenge. Traditional direction-of-arrival (DOA) estimation methods primarily focus on the single-angle estimation with low resolution, failing to satisfy the spatial localization requirements for pipeline defects. Therefore, a high-resolution spatial spectrum estimation algorithm is introduced to realize the two-dimensional DOA estimation. By distributing multiple sensors in a specific geometric configuration to form an array, this method employs the array signal processing technology to accurately obtain the DOA of spatial signals. A uniform circular array (UCA) is employed in the present study to receive signals from pipe defects, and high-precision localization and imaging of defects are achieved based on the two-dimensional minimum variance distortionless response (MVDR) beamforming algorithm, with a relative positioning error of less than 1%. An image classification method based on the convolutional neural network (CNN) is further developed to distinguish the defect types. By constructing a novel CNN model to extract defect features and perform classification, this model achieves a prediction accuracy of 97.50%, which effectively distinguishes between defect types.

physics.app-ph↗