Speed and Separation Monitoring (SSM) is a key enabler for productivity in human-robot collaborative applications, yet its industrial use remains limited by the difficulty of reliably obtaining human-related motion parameters. Although recent research explores AI-based perception to address this challenge, the probabilistic nature and lack of certification of AI methods prevent their deployment as safety-critical systems. This work investigates deterministic strategies for improving SSM efficiency without relying on AI, focusing on zone-adaptation techniques and sensing capabilities that remain fully compatible with functional-safety standards. The work contributes (1) a structured analysis of how motion-adaptive zone formulations can reduce conservatism in current SSM implementations, and (2) a performance-oriented comparison of safety-certified LiDAR and radar sensors regarding velocity measurement. The analysis shows that while LiDAR continues to dominate industrial practice, radar offers several complementary advantages that may significantly enhance SSM performance. These findings motivate further exploration of deterministic, safety-compliant processing methods.

Visible light positioning (VLP) based on received signal strength (RSS) offers a low-cost solution for indoor localization, being easily implemented in a warehouse based on existing infrastructure. However, RSS-based VLP remains challenging in 3D and yields subpar performance compared to 2D due to the larger localization space, as well as the presence of dark spots where many LEDs are not bright enough. This limits the practical use cases of RSS-based VLP in industrial applications. We study the performance of RSS-based VLP on a 3D simulated environment by training various machine learning models, including Gaussian processes and Kolmogorov–Arnold networks on different representations of RSS data. Our findings show that the use of Gaussian processes for predicting distances to LEDs coupled with a logarithmic transformation and multilateration leads to both high-accuracy and high-precision predictions under thermal noise (p95 localization error of 10 cm under 50 dB SNR). With this technique, RSS-based VLP reaches levels of accuracy in our simulated 3D environment that are comparable to those reported for 2D applications, supporting the extension of RSS-based VLP to height-varying industrial use cases.

mmWave radar has seen widespread adoption in several sectors. In particular, 24 GHz radar modules have become increasingly available as low-cost Commercial off-theshelf (COTS) solutions. However, ensuring regulatory compliance for these devices necessitates expensive measurement procedures. This work addresses the need for effective and economical prescreening by measuring the spectral emissions for a representative selection of 24 GHz COTS radar modules. The results show that 2 out of 6 tested modules exhibit out-of-band emissions, demonstrating that the presented pre-screening method can effectively eliminate non-compliant modules before expensive regulatory full certification testing.

This paper presents an optimal calibration scheme and a weighted least squares (LS) localization algorithm for received signal strength (RSS) based visible light positioning (VLP) systems, focusing on the often overlooked impact of light emitting diode (LED) tilt. By optimally calibrating LED tilt and gain, we significantly enhance VLP localization accuracy. Our algorithm outperforms both machine learning Gaussian processes (GPs) and traditional multilateration techniques. Against GPs, it achieves improvements of 58% and 74% in the 50th and 99th percentiles, respectively. When compared to multilateration, it reduces the 50th percentile error from 7.4 cm to 3.2 cm and the 99th percentile error from 25.7 cm to 11 cm. We introduce a low-complexity estimator for tilt and gain that meets the Cramer-Rao lower bound (CRLB) for the mean squared error (MSE), emphasizing its precision and efficiency. Further, we elaborate on optimal calibration measurement placement and refine the observation model to include residual calibration errors, thereby improving localization performance. The weighted LS algorithm's effectiveness is validated through simulations and real-world data, consistently outperforming GPs and multilateration, across various training set sizes and reducing outlier errors. Our findings underscore the critical role of LED tilt calibration in advancing VLP system accuracy and contribute to a more precise model for indoor positioning technologies.

Received signal strength (RSS)-based optical wireless positioning (OWP) systems are becoming popular for indoor localization because they are low-cost and accurate. However, few open-source datasets are available to test and analyze RSS-based OWP systems. In this paper, we collected RSS values at a sampling frequency of 27 Hz, inertial measurement unit (IMU) at a sampling frequency of 200 Hz and the ground truth at a sampling frequency of 160 Hz in two indoor environments. One environment has no obstacles, and the other has a metal column as an obstacle to represent a non-line-of-sight (NLOS) scenario. We recorded data with a vehicle at three different speeds (low, medium and high). The dataset includes over 110 k data points and covers more than 80 min. We also provide benchmark tests to show localization performance using only RSS-based OWP and improve accuracy by combining IMU data via extended kalman filter. The dataset OWP-IMU is open source1 to support further research on indoor localization methods.

The advancement of high-speed and high-power Light-Emitting Diodes (LED) has paved the way for the widespread implementation of Visible Light Positioning (VLP) and Optical Wireless Positioning (OWP). Time Difference of Arrival (TDoA) techniques do not require synchronism between emitters and receivers. However, in TDoA, accurate time difference estimation becomes the key to accurate positioning. Prior work in OWP often neglects Non-Line-of-Sight (NLoS) contributions when modeling the scene response function. In contrast, we adopt an NLoS-aware model and solve the estimation problem in frequency domain via a fast and robust spectral estimation method. Leveraging both ideal model-based simulations and realistic raytracing software, we demonstrate that our approach allows for time difference estimation with machine precision, in the absence of secondary reflections. In the NLoS scenario, our method yields a reduction of the 95th percentile positioning error from 9.5 cm to 5.5 cm over Gaussian pulse fitting in a $1 \mathrm{m} \times$ 1 m experimental frame. Furthermore, our method achieves a significantly higher estimation rate, making it highly suitable for real-time applications.

Received Signal Strength based Visible Light Positioning (RSS-VLP) is an attractive solution for indoor positioning as an enabling technology for future smart environments. Despite this significant importance, there is currently no research focus on the influence of obstacles in the environment. Obstacles could prevent the mobile unit from reaching certain locations, or altogether block the line of sight between the receiver and the light sources. Therefore, this work compares the performance of different machine learning models for visible light positioning using a simulated environment where obstacles can be added. The results shows that machine learning models require much more training data to achieve acceptable performance when shadowing occurs. Gaussian Processes show the best performance out of all evaluated models in environments both with and without obstacles. However, the optimal attainable performance degrades when shadowing is introduced.

Visible light positioning (VLP) offers a cost-effective and accurate method for indoor localization. Gaussian processes (GPs), a data-driven method widely used in the received signal strength (RSS)-based VLP systems, face difficulties when training data are scarce or when forced to extrapolate. In this work, we propose a novel hybrid model, PhyGP, which integrates physics-based models into GPs through Bayesian active learning to enhance extrapolation capabilities without decreasing the interpolation accuracy of GPs. Experimental results, validated on real-world data, demonstrate significant improvements in extrapolation accuracy compared to GPs and in computational efficiency compared to physics-based models. Our approach achieves an improvement in extrapolation accuracy ranging from 32% to 83%, reducing the P50 error from 72 cm to 12 cm at its best performance. Additionally, the PhyGP model offers a four-order magnitude gain in computational efficiency compared with physics-based models.

Indoor navigation and positioning are an essential requirement for numerous industrial applications. Lately, the development of driverless vehicles necessitates the automated parking of vehicles in parking garages. This requires accurate and precise indoor positioning of the vehicles. This work discusses the theoretical basis behind an Optical Wireless Positioning setup in a representative parking garage. The selected hardware and design considerations are elaborated and the performance of the setup is reported. The demonstrated performance shows that 95% of the calculated positions have an error smaller than 12.7 cm compared to the ground truth data.

Time Difference of Arrival (TDoA) based Visible Light Positioning (VLP) and Optical Wireless Positioning (OWP) offer considerable potential over conventional Received Signal Strength (RSS) methods. The current state of the art in TDoA OWP is however limited concerning experimental assessments, mainly focusing on simulations. This work presents experimental TDoA measurements in a proof-of-concept setup. The measurement results demonstrate a 95th percentile accuracy of 5.3 cm in a 50x50 cm area, in the absence of reflections. The susceptibility to reflections is examined experimentally, demonstrating that the performance deterioration can easily be minimized by performing a recalibration.

This work analyzes the achievable precision for pulsed optical wireless time difference of arrival estimation. A statistical signal processing model is presented to derive the Cramér-Rao lower bound on the time difference estimation. An experimental assessment in a small scale lab setup is used to verify the theoretical results. The results identify the system bandwidth and signal-to-noise ratio as the critical system parameters that should be considered to optimize the precision of time difference estimates.

In indoor localization, Received Signal Strength (RSS)-based Visible Light Positioning combined with Multi Layer Perceptrons (MLPs) or Gaussian processes (GPs) has attracted much attention due to its high accuracy. However, there is a lack of detailed investigation on the advantages, disadvantages, and applicability of MLPs and GPs in large datasets collected from representative industrial environments. In this paper, we present a comprehensive comparison and analysis of MLPs and GPs from theoretical and experimental perspectives, focusing on model parameters, complexity, and interpretability. Our study demonstrates that while GPs outperform MLPs on small datasets, they exhibit drawbacks such as high computational cost on larger datasets. Furthermore, our investigation reveals that including Batch Normalization (BN) layers in MLPs enhances their generalization and suppresses outliers in prediction. To address the issues of scalability and interpretability, we introduce the Deep Kernel Learning (DKL) model as a solution, supported by both theoretical and experimental findings.

As visible light positioning combines illumination and indoor localization, the relationship between the uniformity index as a quality measurement of the illumination and the precision of the positioning technique is investigated. It is demonstrated that the classic multilateration approach leads to a degradation of the accuracy as the uniformity improves. When a Gaussian Process is deployed, the accuracy improves for better uniformity indices. Further normalization of the area size leads to a generic curve that can be used to estimate the required training set size when a Gaussian Process is used given the required accuracy and observation plane size.

In this paper, a novel three-dimensional (3D) indoor visible light positioning (VLP) algorithm is proposed based on the spatial modulation (SM) and its error performance assessed as compared to the conventional received signal strength (RSS)-based 3D VLP systems. As contrasted to the traditional VLP system, the proposed SM-based 3D VLP system first estimates the optical channel gain between the transmitting light-emitting diodes (LEDs) and the two photo detectors (PDs) attached to the user by a pilot-based channel estimation technique. Then, unknown 3D positions of the receiver are determined by the trilateration algorithm with distances computed from the estimates of the channel gains. Consequently, the 3D VLP system achieves an interference-free transmission with increased spectral efficiency and without the need for a demultiplexing process at the receiving end. The algorithm’s performance is evaluated regarding positioning error by applying the SM over four LEDs and the number of pilots selected as a function of the environmental signal-to-noise ratios (SNRs). The computer simulation results show that the positioning errors are obtained in an order of magnitude smaller than RSS-based techniques in an indoor industrial environment. This is mainly because the distances involved in determining the 3D positions can be determined more precisely by the pilot-aided channel estimation method without creating any data rate problem in transmission due to the higher spectral efficiency of the SM.

Indoor Positioning Systems act as an important technology to provide real-time location estimation, enabling a large variety of industrial applications. In this context, Optical Wireless Positioning employs the propagation characteristics of optical signals as a means to calculate an accurate and precise position. While Visible Light Positioning focuses on the use of LED lighting to support both positioning and illumination simultaneously, Infrared-based systems also offer viable positioning solutions featuring distinct advantages and drawbacks over their visible light counterparts. The selection of the used wavelength thus proves to be an important design consideration for an Optical Wireless Positioning system. This work summarises the main differences and trade-offs fundamental to the selection of the wavelength, and compares them in order to make an informed decision on the selection.

Visible Light Positioning (VLP) is a promising indoor localization technology for providing highly accurate positioning.In this work, a VLP implementation is employed to estimate the position of a vehicle in a room using the Received Signal Strength (RSS) and fixed LED-based light transmitters.Classical VLP approaches use lateration or angulation based on a wireless propagation model to obtain location estimations.However, previous work has shown that machine learning models such as Gaussian processes (GP) achieve better performance and are more robust in general, particularly in presence of non-ideal environmental conditions.As a downside, Machine Learning (ML) models require a large collection of RSS samples, which can be time-consuming to acquire.In this work, a sampling scheme based on active learning (AL) is proposed to automate the vehicle motion and to accelerate the data collection.The scheme is tested on experimental data from a RSS-based VLP setup and compared with different settings to a simple random sampling.

New concepts for next-generation wireless systems are being developed. It is expected that these 6G and beyond systems will incorporate more than only communication, but also sensing, positioning, (deep) edge computing, and other services. The discussed measurement facility and approach, named Techtile, is an open, both in design and operation, and unique testbed to evaluate these newly envisioned systems. Techtile is a multi-functional and versatile testbed, providing fine-grained distributed resources for new communication, positioning and sensing technologies. The facility enables experimental research on hyper-connected interactive environments and validation of new algorithms and topologies. The backbone connects 140 resource units equipped with edge computing devices, software-defined radios (SDRs), sensors, and LED sources. By doing so, different network topologies and local-versus-central computing can be assessed. The introduced diversity of i) the technologies (e.g., RF, acoustics and light), ii) the distributed resources and iii) the interconnectivity allows exploring more degrees and new types of diversity, which can be investigated in this testbed.

The EU COST Action NEWFOCUS is focused on investigating radical solutions with the potential to impact the design of future wireless networks. It aims to address some of the challenges in OWC and establish it as an efficient technology that can satisfy the demanding requirements of backhaul and access network levels in 5G networks. This also includes the use of hybrid links that associate OWC with radiofrequency or wired/fiber-based technologies. The focus of this White Paper is on the use of optical wireless communication (OWC) as enabling technology in a range of areas outlined in HE's Pillar II including Health, Manufacturing, Intelligent Transportation Systems (ITS), Unmanned Aerial Vehicles and Network and Protocol.

The research interest on indoor Location-Based Services (LBS) has increased during the last years, especially using LED lighting, since they can deal with the dual functionality of lighting and localization with centimetric accuracy. There are several positioning approaches using lateration and angular methods. These methods typically rely on the physical model to deal with the multipath effect, environmental fluctuations, calibration of the optical setup, etc. A recent approach is the use of Machine Learning (ML) techniques. ML techniques provide accurate location estimates based on observed data without requiring the underlying physical model to be described. This work proposes an optical indoor local positioning system based on multiple LEDs and a quadrant photodiode plus an aperture. Different frequencies are used to allow the simultaneous emission of all transmitted signals and their processing at the receiver. For that purpose, two algorithms are developed. First, a triangulation algorithm based on Angle of Arrival (AoA) measurements, which uses the Received Signal Strength (RSS) values from every LED on each quadrant to determine the image points projected from each emitter on the receiver and, then, implements a Least Squares Estimator (LSE) and trigonometric considerations to estimate the receiver's position. Secondly, the performance of a data-driven approach using Gaussian Processes is evaluated. The proposals have been experimentally validated in an area of 3 × 3m$^{2}$ and a height of 1.3 m (distance from transmitters to receiver). The experimental tests achieve p50 and p95 2D absolute errors below 9.38 cm and 21.94 cm for the AoA-based triangulation algorithm, and 3.62 cm and 16.65 cm for the Gaussian Processes.

Visible Light Positioning (VLP) provides highly accurate and precise indoor positioning. However, near reflective surfaces, Non-Line-of-Sight (NLOS) contributions compromise the accuracy of VLP. This work demonstrates that the presence of these contributions is detectable based on the polarization state by employing a linear polarizer.