Von Mises Based Uncertainty Quantification for Closely Spaced Automotive Radar Targets

This work investigates uncertainty-aware deep learning approaches for direction of arrival (DOA) estimation in automotive radar, focusing on probabilistic modeling and downstream integration. A circular-statistics-based von Mises (VM) ensemble (ENS) is compared with an evidential deep learning (EDL) framework based on a normal inverse gamma formulation, yielding a Student t predictive distribution in the Euclidean domain. The ENS framework produces angular predictions parameterized by (mu, kappa), enabling interpretable uncertainty aligned with directional geometry. Performance is evaluated under in distribution and multiple out-of-distribution conditions using risk coverage and ROC or AUROC analyses. Results indicate that ENS achieves lower uncertainty under nominal conditions and exhibits stronger sensitivity to severe perturbations, whereas EDL provides smoother uncertainty variation and slightly improved ranking consistency. Importantly, the ENS representation enables direct probabilistic integration into association modules via closed form VM likelihoods, facilitating a unified detection tracking pipeline. These findings highlight a trade-off between geometric consistency and statistical generality in uncertainty-aware DOA estimation.

Empirical characterization of the Translational acoustic-RF communication channel

Translational acoustic-radio frequency (TARF) communication paves the way for translating information from an underwater acoustic signal to the over-the-air (OTA) electromagnetic receiver through the medium interface. The study and characterization of the channel is essential for establishing a reliable communication link. Although channel modeling has been extensively studied for OTA and underwater channels, the amplitude characteristics of the TARF cross-medium channel have not been investigated in comparison with well-known distributions to date. In this work, we first refine the signal model to incorporate the effects of the wavefront-water surface interactions. With the help of numerical and graphical methods, we then attempt to characterize the cross-medium channel with empirical data using existing models developed for OTA and underwater channels. We further evaluate channel linearity and time invariance empirically. Observations from these studies over multiple experiments are detailed with additional discussions that enable better channel characterization to develop reliable and consistent cross-medium TARF communication in challenging scenarios.

Statistical Inference Framework for Extended Target Detection in mmWave Automotive Radar

Millimeter wave (mmWave) radar systems, owing to their large bandwidth, provide fine range resolution that enables the observation of multiple scatterers originating from a single automotive target commonly referred to as an extended target. Conventional CFAR-based detection algorithms typically treat these scatterers as independent detections, thereby discarding the spatial scattering structure intrinsic to the target. To preserve this scattering spread, this paper proposes a Range-Doppler (RD) segment framework designed to encapsulate the typical scattering profile of an automobile. The statistical characterization of the segment is performed using Maximum Likelihood Estimation (MLE) and posterior density modeling facilitated through Gibbs Markov Chain Monte Carlo (MCMC) sampling. A skewness-based test statistic, derived from the estimated statistical model, is introduced for binary hypothesis classification of extended targets. Additionally, the paper presents a detection pipeline that incorporates Intersection over Union (IoU) and segment centering based on peak response, optimized to work within a single dwell. Extensive evaluations using both simulated and real-world datasets demonstrate the effectiveness of the proposed approach, underscoring its suitability for automotive radar applications through improved detection accuracy.

KAN-powered large-target detection for automotive radar

This paper presents a novel radar signal detection pipeline focused on detecting large targets such as cars and SUVs. Traditional methods, such as Ordered-Statistic Constant False Alarm Rate (OS-CFAR), commonly used in automotive radar, are designed for point or isotropic target models. These may not adequately capture the Range-Doppler (RD) scattering patterns of larger targets, especially in high-resolution radar systems. Additional modules such as association and tracking are necessary to refine and consolidate the detections over multiple dwells. To address these limitations, we propose a detection technique based on the probability density function (pdf) of RD segments, leveraging the Kolmogorov-Arnold neural network (KAN) to learn the data and generate interpretable symbolic expressions for binary hypotheses. Beside the Monte-Carlo study showing better performance for the proposed KAN expression over OS-CFAR, it is shown to exhibit a probability of detection (PD) of 96% when transfer learned with field data. The false alarm rate (PFA) is comparable with OS-CFAR designed with PFA = $10^{-6}$. Additionally, the study also examines impact of the number of pdf bins representing RD segment on performance of the KAN-based detection.

Beamspace-based Sensing in Dynamic Joint Communication and Sensing Systems

Dual-function radar communication (DFRC) systems incorporate both radar and communication functions by sharing spectrum, hardware and RF signal processing chains. Future technologies, such as 6G, are envisioned to support multiple communication platforms along with radar sensing, thus leading to high dynamism and competition for the available resources. In such settings, whenever communication takes precedence, a likely scenario is dynamically changing RF chain and antenna availability for sensing. This necessitates real-time beam redesign to cover the field-of-view (FOV), solving which is intractable via computationally expensive optimization approaches. We propose that classic windowing techniques are still relevant and much more practical than optimization methods in such dynamic scenarios. Specifically, parametrized windows can be used in a strategic way to adapt to varying resource availability while sustaining sensing performance.