Bing Zhu

4D automotive radars have gained increasing attention for autonomous driving due to their low cost, robustness, and inherent velocity measurement capability. However, existing 4D radar-based 3D detectors rely heavily on pillar encoders for BEV feature extraction, where each point contributes to only a single BEV grid, resulting in sparse feature maps and degraded representation quality. In addition, they also optimize bounding box attributes independently, leading to sub-optimal detection accuracy. Moreover, their inference speed, while sufficient for high-end GPUs, may fail to meet the real-time requirement on vehicle-mounted embedded devices. To overcome these limitations, an efficient and effective Gaussian-based 3D detector, namely RadarGaussianDet3D is introduced, leveraging Gaussian primitives and distributions as intermediate representations for radar points and bounding boxes. In RadarGaussianDet3D, a novel Point Gaussian Encoder (PGE) is designed to transform each point into a Gaussian primitive after feature aggregation and employs the 3D Gaussian Splatting (3DGS) technique for BEV rasterization, yielding denser feature maps. PGE exhibits exceptionally low latency, owing to the optimized algorithm for point feature aggregation and fast rendering of 3DGS. In addition, a new Box Gaussian Loss (BGL) is proposed, which converts bounding boxes into 3D Gaussian distributions and measures their distance to enable more comprehensive and consistent optimization. Extensive experiments on TJ4DRadSet and View-of-Delft demonstrate that RadarGaussianDet3D achieves high detection accuracy while delivering substantially faster inference, highlighting its potential for real-time deployment in autonomous driving.

Millimeter wave (mmWave) radar is a non-intrusive, privacy-preserving, and cost-effective device, shown to be a viable alternative to RGB cameras for indoor human pose estimation. However, the challenge lies in fully leveraging the reflected radar signals for accurate pose estimation. To address this major challenge, this paper introduces a probability map guided multi-format feature fusion model, ProbRadarM3F. This is a radar feature extraction framework using a traditional FFT method in parallel with a probability map based positional encoding method. ProbRadarM3F fuses the traditional heatmap features and the positional features, then effectively achieves the estimation of 14 keypoints of the human body. Experimental evaluation on the HuPR dataset proves the effectiveness of $69.9\%$ in average precision (AP). The emphasis of our study is on utilizing position information in radar signals for estimating human skeletal pose. This provides direction for investigating other potential non-redundant information from mmWave radar.

As the previous state-of-the-art 4D radar-camera fusion-based 3D object detection method, LXL utilizes the predicted image depth distribution maps and radar 3D occupancy grids to assist the sampling-based image view transformation. However, the depth prediction lacks accuracy and consistency, and the concatenation-based fusion in LXL impedes the model robustness. In this work, we propose LXLv2, where modifications are made to overcome the limitations and improve the performance. Specifically, considering the position error in radar measurements, we devise a one-to-many depth supervision strategy via radar points, where the radar cross section (RCS) value is further exploited to adjust the supervision area for object-level depth consistency. Additionally, a channel and spatial attention-based fusion module named CSAFusion is introduced to improve feature adaptiveness. Experimental results on the View-of-Delft and TJ4DRadSet datasets show that the proposed LXLv2 can outperform LXL in detection accuracy, inference speed and robustness, demonstrating the effectiveness of the model.

In autonomous driving, LiDAR and radar are crucial for environmental perception. LiDAR offers precise 3D spatial sensing information but struggles in adverse weather like fog. Conversely, radar signals can penetrate rain or mist due to their specific wavelength but are prone to noise disturbances. Recent state-of-the-art works reveal that the fusion of radar and LiDAR can lead to robust detection in adverse weather. Current approaches typically fuse features from various data sources using basic convolutional/transformer network architectures and employ straightforward label assignment strategies for object detection. However, these methods have two main limitations: they fail to adequately capture feature interactions and lack consistent regression constraints. In this paper, we propose a bird’s-eye view fusion learning-based anchor box-free object detection system. Our approach introduces a novel interactive transformer module for enhanced feature fusion and an advanced label assignment strategy for more consistent regression, addressing key limitations in existing methods. Specifically, experiments show that, our approach’s average precision ranks 1 ^st and significantly outperforms the state-of-the-art method by 13.1% and 19.0% at Intersection of Union (IoU) of 0.8 under “Clear+Foggy" training conditions for “Clear" and “Foggy" testing, respectively. Our code repository is available at: https://github.com/yyxr75/RaLiBEV.

In this paper, a model predictive control (MPC) framework is proposed for finite-time stabilization of linear and nonlinear discrete-time systems subject to state and control constraints. The proposed MPC framework guarantees the finite-time convergence property by assigning the control horizon equal to the dimension of the overall system, and only penalizing the terminal cost in the optimization, where the stage costs are not penalized explicitly. A terminal inequality constraint is added to guarantee the feasibility and stability of the closed-loop system. Initial feasibility can be improved via augmentation. The finite-time convergence of the proposed MPC is proved theoretically, and is supported by simulation examples.