arXiv subjects

Jan Steckel

Publications and source records attributed to Jan Steckel.

At least 19 recordsLinked to original sources

arXiv2026

Intelligent Road Condition Monitoring using 3D In-Air SONAR Sensing

In this paper, we investigate the capabilities of in-air 3D SONAR sensors for the monitoring of road surface conditions. Concretely, we consider two applications: Road material classification and Road damage detection and classification. While such tasks can be performed with other sensor modalities, such as camera sensors and LiDAR sensors, these sensor modalities tend to fail in harsh sensing conditions, such as heavy rain, smoke or fog. By using a sensing modality that is robust to such interference, we enable the creation of opportunistic sensing applications, where vehicles performing other tasks (garbage collection, mail delivery, etc.) can also be used to monitor the condition of the road. For these tasks, we use a single dataset, in which different types of damages are annotated, with labels including the material of the road surface. In the material classification task, we differentiate between three different road materials: Asphalt, Concrete and Element roads. In the damage detection and classification task, we determine if there is damage, and what type of damage (independent of material type), without localizing the damage. We are succesful in determining the road surface type from SONAR sensor data, with F1 scores approaching 90% on the test set, but find that for the detection of damages performace lags, with F1 score around 75%. From this, we conclude that SONAR sensing is a promising modality to include in opportunistic sensing-based pavement management systems, but that further research is needed to reach the desired accuracy.

cs.CV↗

arXiv2026

Hardware-Accelerated Geometrical Simulation of Biological and Engineered In-Air Ultrasonic Systems

The deployment of in-air acoustic sensors for industrial monitoring and autonomous robotics has grown significantly, often drawing inspiration from biological echolocation. However, developing and validating these systems in existing simulation frameworks remains challenging due to the computational cost of simulating high-frequency wave propagation in large, dynamic, and complex environments. While wave-based methods offer high accuracy, they scale poorly with frequency and volume. Conversely, existing geometric acoustic solvers often lack support for dynamic scenes, complex diffraction, or closed-loop robotic integration. In this work, we introduce SonoTraceUE, a high-fidelity acoustic simulation framework built as a plugin for Unreal Engine. By using a hardware-accelerated ray tracing-based specular reflection model, and a curvature-based Monte Carlo diffraction model, the system enables near real-time simulation of active and passive acoustic sensing in dynamic, multi-material environments. We validate the framework through two distinct experimental domains: a bioacoustic study and a robotics experiment. Our results demonstrate that SonoTraceUE achieves high correlation with real-world spectral and spatial data. The framework provides a versatile platform for synthetic data generation, hypothesis testing in bioacoustics, and the rapid prototyping of closed-loop robotic systems that use acoustic sensing.

eess.SP↗

arXiv2026

LLM-Driven 3D Scene Generation of Agricultural Simulation Environments

Procedural generation techniques in 3D rendering engines have revolutionized the creation of complex environments, reducing reliance on manual design. Recent approaches using Large Language Models (LLMs) for 3D scene generation show promise but often lack domain-specific reasoning, verification mechanisms, and modular design. These limitations lead to reduced control and poor scalability. This paper investigates the use of LLMs to generate agricultural synthetic simulation environments from natural language prompts, specifically to address the limitations of lacking domain-specific reasoning, verification mechanisms, and modular design. A modular multi-LLM pipeline was developed, integrating 3D asset retrieval, domain knowledge injection, and code generation for the Unreal rendering engine using its API. This results in a 3D environment with realistic planting layouts and environmental context, all based on the input prompt and the domain knowledge. To enhance accuracy and scalability, the system employs a hybrid strategy combining LLM optimization techniques such as few-shot prompting, Retrieval-Augmented Generation (RAG), finetuning, and validation. Unlike monolithic models, the modular architecture enables structured data handling, intermediate verification, and flexible expansion. The system was evaluated using structured prompts and semantic accuracy metrics. A user study assessed realism and familiarity against real-world images, while an expert comparison demonstrated significant time savings over manual scene design. The results confirm the effectiveness of multi-LLM pipelines in automating domain-specific 3D scene generation with improved reliability and precision. Future work will explore expanding the asset hierarchy, incorporating real-time generation, and adapting the pipeline to other simulation domains beyond agriculture.

cs.CV↗

arXiv2025

Predictive Modeling of Maritime Radar Data Using Transformer Architecture

Maritime autonomous systems require robust predictive capabilities to anticipate vessel motion and environmental dynamics. While transformer architectures have revolutionized AIS-based trajectory prediction and demonstrated feasibility for sonar frame forecasting, their application to maritime radar frame prediction remains unexplored, creating a critical gap given radar's all-weather reliability for navigation. This survey systematically reviews predictive modeling approaches relevant to maritime radar, with emphasis on transformer architectures for spatiotemporal sequence forecasting, where existing representative methods are analyzed according to data type, architecture, and prediction horizon. Our review shows that, while the literature has demonstrated transformer-based frame prediction for sonar sensing, no prior work addresses transformer-based maritime radar frame prediction, thereby defining a clear research gap and motivating a concrete research direction for future work in this area.

cs.CV↗

arXiv2025

Delay-Multiply-And-Sum Beamforming for Real-Time In-Air Acoustic Imaging

In-air acoustic imaging systems demand beamforming techniques that offer a high dynamic range and spatial resolution while also remaining robust. Conventional Delay-and-Sum (DAS) beamforming fails to meet these quality demands due to high sidelobes, a wide main lobe and the resulting low contrast, whereas advanced adaptive methods are typically precluded by the computational cost and the single-snapshot constraint of real-time field operation. To overcome this trade-off, we propose and detail the implementation of higher-order non-linear beamforming methods using the Delay-Multiply-and-Sum technique, coupled with Coherence Factor weighting, specifically adapted for ultrasonic in-air microphone arrays. Our efficient implementation allows for enabling GPU-accelerated, real-time performance on embedded computing platforms. Through validation against the DAS baseline using simulated and real-world acoustic data, we demonstrate that the proposed method provides significant improvements in image contrast, establishing higher-order non-linear beamforming as a practical, high-performance solution for in-air acoustic imaging.

eess.SP↗

arXiv2025

Ruggedized Ultrasound Sensing in Harsh Conditions: eRTIS in the wild

We present eRTIS, a rugged, embedded ultrasound sensing system for use in harsh industrial environments. The system features a broadband capacitive transducer and a 32-element MEMS microphone array capable of 2D and 3D beamforming. A modular hardware architecture separates sensing and processing tasks: a high-performance microcontroller handles excitation signal generation and data acquisition, while an NVIDIA Jetson module performs GPU-accelerated signal processing. eRTIS supports external synchronization via a custom controller that powers and coordinates up to six devices, either simultaneously or in a defined sequence. Additional synchronization options include bidirectional triggering and in-band signal injection. A sealed, anodized aluminum enclosure with passive cooling and IP-rated connectors ensures reliability in challenging conditions. Performance is demonstrated in three field scenarios: harbor mooring, off-road robotics, and autonomous navigation in cluttered environments, demonstrates that eRTIS provides robust sensing in situations where optical systems degrade.

eess.SY↗

arXiv2025

Towards In-Air Ultrasonic QR Codes: Deep Learning for Classification of Passive Reflector Constellations

In environments where visual sensors falter, in-air sonar provides a reliable alternative for autonomous systems. While previous research has successfully classified individual acoustic landmarks, this paper takes a step towards increasing information capacity by introducing reflector constellations as encoded tags. Our primary contribution is a multi-label Convolutional Neural Network (CNN) designed to simultaneously identify multiple, closely spaced reflectors from a single in-air 3D sonar measurement. Our initial findings on a small dataset confirm the feasibility of this approach, validating the ability to decode these complex acoustic patterns. Secondly, we investigated using adaptive beamforming with null-steering to isolate individual reflectors for single-label classification. Finally, we discuss the experimental results and limitations, offering key insights and future directions for developing acoustic landmark systems with significantly increased information entropy and their accurate and robust detection and classification.

eess.SP↗

arXiv2025

LiDAR-BIND-T: Improved and Temporally Consistent Sensor Modality Translation and Fusion for Robotic Applications

This paper extends LiDAR-BIND, a modular multi-modal fusion framework that binds heterogeneous sensors (radar, sonar) to a LiDAR-defined latent space, with mechanisms that explicitly enforce temporal consistency. We introduce three contributions: (i) temporal embedding similarity that aligns consecutive latent representations, (ii) a motion-aligned transformation loss that matches displacement between predictions and ground truth LiDAR, and (iii) windowed temporal fusion using a specialised temporal module. We further update the model architecture to better preserve spatial structure. Evaluations on radar/sonar-to-LiDAR translation demonstrate improved temporal and spatial coherence, yielding lower absolute trajectory error and better occupancy map accuracy in Cartographer-based SLAM (Simultaneous Localisation and Mapping). We propose different metrics based on the Fr\'echet Video Motion Distance (FVMD) and a correlation-peak distance metric providing practical temporal quality indicators to evaluate SLAM performance. The proposed temporal LiDAR-BIND, or LiDAR-BIND-T, maintains modular modality fusion while substantially enhancing temporal stability, resulting in improved robustness and performance for downstream SLAM.

cs.CV↗

arXiv2025

Resource-Aware Neural Network Pruning Using Graph-based Reinforcement Learning

This paper presents a novel approach to neural network pruning by integrating a graph-based observation space into an AutoML framework to address the limitations of existing methods. Traditional pruning approaches often depend on hand-crafted heuristics and local optimization perspectives, which can lead to suboptimal performance and inefficient pruning strategies. Our framework transforms the pruning process by introducing a graph representation of the target neural network that captures complete topological relationships between layers and channels, replacing the limited layer-wise observation space with a global view of network structure. The core innovations include a Graph Attention Network (GAT) encoder that processes the network's graph representation and generates a rich embedding. Additionally, for the action space we transition from continuous pruning ratios to fine-grained binary action spaces which enables the agent to learn optimal channel importance criteria directly from data, moving away from predefined scoring functions. These contributions are modelled within a Constrained Markov Decision Process (CMDP) framework, allowing the agent to make informed pruning decisions while adhering to resource constraints such as target compression rates. For this, we design a self-competition reward system that encourages the agent to outperform its previous best performance while satisfying the defined constraints. We demonstrate the effectiveness of our approach through extensive experiments on benchmark datasets including CIFAR-10, CIFAR-100, and ImageNet. The experiments show that our method consistently outperforms traditional pruning techniques, showing state-of-the-art results while learning task-specific pruning strategies that identify functionally redundant connections beyond simple weight magnitude considerations.

cs.LG↗

arXiv2025

High-Density MIMO Localization Using a 32x64 Ultrasonic Transducer-Microphone Array with Real-Time Data Streaming

In this work, we present a novel ultrasonic array system designed for high-precision localization using a large-scale MIMO (Multiple-Input Multiple-Output) architecture. The system combines 32 transmitters with 62 microphones, creating an extended virtual aperture that improves channel separability and spatial resolution. Each transmitter is excited by a random-phase multisine within the ultrasonic band, which reduces inter-channel correlation and increases robustness against multipath. The feasibility of the approach is demonstrated through simulations of reflector imaging and analysis of channel separation under realistic transducer bandwidth constraints. Results show that MIMO processing enables improved separation of reflectors compared to single-emitter configurations, although practical limitations such as transducer bandwidth reduce the achievable channel isolation.

eess.SP↗

arXiv2025

nRTIS: Low-Cost Real-Time 3D Sonar Imaging Circular Array Supporting Beamforming for Industrial Applications

Conventional ultrasonic inspection systems rely on phased arrays and high-performance computing hardware, making them costly, bulky, and unsuitable for portable or embedded use. In this work, we present nRTIS (nano Real-Time 3D Imaging Sonar), a compact ultrasonic sensing platform built around a circular array of MEMS microphones and a central ultrasonic transducer. The device achieves real-time acquisition through an RP2350 microcontroller and high-speed USB transfer. We validate the system using both simulations and controlled experiments: point spread function (PSF) simulations demonstrate beamforming resolution and sidelobe suppression, while reflector measurements confirm robust data acquisition. These results highlight the potential of nRTIS for scalable industrial applications such as weld inspection, pipe mapping, and robotic navigation.

eess.SP↗

arXiv2025

ConamArray: A 32-Element Broadband MEMS Ultrasound Transducer Array

This paper presents the ConamArray, a compact broadband ultrasound transducer array composed of 32 MEMS loudspeakers. Unlike conventional broadband transducers, which are typically large and require high driving voltages, the proposed array combines small form factor MEMS devices in a staggered two-row configuration to enable beam steering across a wide ultrasonic band. A dual-microcontroller back-end with synchronized multi-DAC outputs provides flexible waveform generation and runtime steering control. Both simulations and anechoic chamber measurements demonstrate that the ConamArray achieves stable beam steering, while also revealing the onset of grating lobes when steering to larger angles. These results confirm the feasibility of broadband beam steering using MEMS technology, opening new opportunities for applications in ultrasonic imaging, localization, and bio-inspired robotics.

eess.SY↗

arXiv2025

PhysioEdge: Multimodal Compressive Sensing Platform for Wearable Health Monitoring

The integration of compressive sensing with real-time embedded systems opens new possibilities for efficient, low-power biomedical signal acquisition. This paper presents a custom hardware platform based on the RP2350 micro-controller, tailored for synchronized multi-modal biomedical monitoring. The system is capable of capturing cardiopulmonary sounds, along with biopotential signals such as phonocardiography (PCG), electrocardiography (ECG) and electromyography (EMG), photoplethysmography (PPG), and inertial measurement unit (IMU) data for posture recognition. To ensure sample-accurate synchronization, a Sub-1GHz radio system is used across multiple nodes. Wi-Fi and Bluetooth connectivity enable centralized data aggregation. Experimental results demonstrate the achieved decrease in power consumption when using compressive sensing, efficient multi-node synchronization, and scalability for wireless biomedical monitoring applications. The compact form factor and low-cost design make it suitable for various medical applications, including remote healthcare and long-term monitoring.

eess.SY↗

arXiv2025

ASVSim (AirSim for Surface Vehicles): A High-Fidelity Simulation Framework for Autonomous Surface Vehicle Research

The transport industry has recently shown significant interest in unmanned surface vehicles (USVs), specifically for port and inland waterway transport. These systems can improve operational efficiency and safety, which is especially relevant in the European Union, where initiatives such as the Green Deal are driving a shift towards increased use of inland waterways. At the same time, a shortage of qualified personnel is accelerating the adoption of autonomous solutions. However, there is a notable lack of open-source, high-fidelity simulation frameworks and datasets for developing and evaluating such solutions. To address these challenges, we introduce AirSim for Surface Vehicles (ASVSim), an open-source simulation framework specifically designed for autonomous shipping research in inland and port environments. The framework combines simulated vessel dynamics with marine sensor simulation capabilities, including radar and camera systems and supports the generation of synthetic datasets for training computer vision models and reinforcement learning (RL) agents. Built upon Cosys-AirSim, ASVSim provides a comprehensive platform for developing autonomous navigation algorithms and generating synthetic datasets. The simulator supports research of both traditional control methods and deep learning-based approaches. Through experiments in waterway segmentation and autonomous navigation, we demonstrate the capabilities of the simulator in these research areas. ASVSim is provided as an open-source project under the MIT license, making autonomous navigation research accessible to a larger part of the ocean engineering community. See https://github.com/BavoLesy/ASVSim.

cs.RO↗

arXiv2025

A Wireless Self-Calibrating Ultrasound Microphone Array with Sub-Microsecond Synchronization

We present a novel system architecture for a distributed wireless, self-calibrating ultrasound microphone network for synchronized in-air acoustic sensing. Once deployed the embedded nodes determine their position in the environment using the infrared optical tracking system found in the HTC Vive Lighthouses. After self-calibration, the nodes start sampling the ultrasound microphone while embedding a synchronization signal in the data which is established using a wireless Sub-1GHz RF link. Data transmission is handled via the Wi-Fi 6 radio that is embedded in the nodes' SoC, decoupling synchronization from payload transport. A prototype system with a limited amount of network nodes was used to verify the proposed distributed microphone array's wireless data acquisition and synchronization capabilities. This architecture lays the groundwork for scalable, deployable ultrasound arrays for sound source localization applications in bio-acoustic research and industrial acoustic monitoring.

eess.SP↗

arXiv2025

Dynamically Tunable Helical Antenna

Unmanned aerial FPV systems demand ultra-low latency, high-reliability communication links. At high speeds and in cluttered environments, Doppler shifts and rapid multipath changes can dramatically raise packet error rates. This paper investigates these phenomena in the context of ExpressLRS (ELRS) long-range FPV control links and demonstrates a novel solution: real-time geometry tuning of a circularly polarized helical antenna array. This study integrates Maxwell-equation-based full-wave simulations (via Ansys HFSS) with controlled, blind field trials to validate performance. A new analysis framework incorporates Doppler-induced frequency offset into the antenna's radiation pattern and the system's error model. Compared to a conventional fixed antenna, the adaptive helical array shows a 20-30% PER reduction when drones exceed 150 mph. The adaptive system automatically adjusts coil pitch and diameter to retune the antenna as flight parameters (velocity, attitude) change. Measured VSWR stays near unity, preventing transmitter reflection spikes. RSSI variation is reduced by half, indicating stronger link stability in urban multi-path. A regression analysis confirms that the reduction in PER due to tuning is highly statistically significant. Calibration data and error analyses are provided to validate our methodology. These findings advance the understanding of high-mobility UAV communication channels and demonstrate that reconfigurable hardware-here, mechanically tunable helices-can effectively counter Doppler and multi-path impairments. The findings inform new design principles for UAV antenna arrays and suggest a path toward AI-integrated adaptive RF systems for drone swarms and racing platforms.

eess.SP↗

arXiv2025

Towards Autonomous 1/8th Offroad RC Racing -- The TruggySense Educational Platform

This paper presents a state-of-the-art Data Acquisition System designed for off-road conditions, deployed on a Team Corally Kagama 1/8 Remote Controlled Vehicle. The system is intended to support Advanced Driver Assistance Systems in an educational context by providing valuable, consistent, and representative data. Key measurement systems are discussed to enable insights into the Remote Controlled Vehicles stability during and after off-road races. Furthermore, four experiments where conducted to evaluate the Data Acquisition Systems accuracy, stability, and consistency in replicating real-world vehicle behavior. The proposed Data Acquisition System platform serves as a solid foundation for use in engineering education, enabling integration with various Advanced Driver Assistance Systems algorithms to enhance vehicle control and overall performance, offering a new dimension to off-road racing. Additionally, realtime telemetry enables verification and validation of Advanced Driver Assistance Systems algorithms based on the live operating state of the Radio Controlled Vehicle during races

eess.SY↗

arXiv2025

Phase-Center-Constrained Beamforming for Minimizing Phase-Center Displacement

Accurate knowledge and control of the phase center in antenna arrays is essential for high-precision applications such as Global Navigation Satellite Systems (GNSS), where even small displacements can introduce significant localization errors. Traditional beamforming techniques applied to array antennas often neglect the variation of the phase center, resulting in unwanted spatial shifts, and in consequence, localization errors. In this work, we propose a novel beamforming algorithm, called Phase-Center-Constrained Beamforming (PCCB), which explicitly minimizes the displacement of the phase center (Phase Center Offset, PCO) while preserving a chosen directional gain. We formulate the problem as a constrained optimization problem and incorporate regularization terms that enforce energy compactness and beampattern fidelity. The resulting PCCB approach allows for directional gain control and interference nulling while significantly reducing PCO displacement. Experimental validation using a simulated GNSS antenna array demonstrates that our PCCB approach achieves a fivefold reduction in PCO shift compared to the PCO shifts obtained when using conventional beamforming. A stability analysis across multiple random initializations confirms the robustness of our method and highlights the benefit of repeated optimization. These results indicate that our PCCB approach can serve as a practical and effective solution for decreasing phase center variability.

eess.SP↗