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.

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 $\mathbf{P 5 0}$ 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.

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 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.

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.

In this work the scalability of Artificial Neural Networks for RSS-based visible light positioning is investigated in a large and representative industrial experimental setup. More specifically, the performance in terms of localization accuracy of Multi Layer Perceptron (MLP) models is studied by comparing an MLP model that provides localization over the entire area to a cell based modular approach of multiple neural networks that individually provide localization in a subspace of the experimental setup. The main conclusions are that both approaches have the potential to deliver accurate localization in this challenging setup with a p50 error of well below 10cm. However, in terms of finding suitable model hyperparameters and scalability to even larger setups, the second approach provides more robustness.

Localization based on visible light is a novel technique for indoor positioning that provides a number of advantages over traditional radio frequency based approaches. An important step in the deployment of visible light positioning systems is the calibration procedure, during which environmental parameters such as the positions of light sources are determined. This work presents a proof-of-concept approach to obtain these parameters in an efficient manner by using a mobile robot. This robot builds a map of the environment, and adds the location and identifier of optical transmitters to this map. With this approach, light source modulation frequencies can be estimated with sufficient accuracy to uniquely identify each source. Additionally, the inter-LED distance has an average accuracy of less than 10 cm compared to the real distance.

This paper assesses the accuracy of a three-dimensional Visible Light Positioning (VLP) algorithm for two different Light Emitting Diode (LED) configurations using the same four LEDs, but mounted at different locations on the ceiling. The two configurations are both simulated and measured at 22801 test points. It is observed that a classic square LED configuration results in position ambiguities, causing errors up to several meters. Alternatively, a star-shaped LED configuration is able to uniquely reconstruct the photodiode's location. For LEDs at a height of approximately 3 m above the receiver, median errors of 12.7 cm and maximal errors of 21.1 cm are experimentally obtained, showcasing the applicability of 3D VLP for drone navigation.

With the rise of solid state lighting, wireless positioning based on visible light is becoming more appealing. However, current visible light positioning systems require additional hardware at the transmitter end in order to modulate the light intensity. A receiver demultiplexes the combined signal from multiple sources into its components, which are then used by the positioning algorithm. This paper investigates the possibility of using unmodulated visible light for mobile robot positioning. Less hardware is required, consequently cost and complexity are much lower. Position estimation is achieved by modeling the received signal strength inside a room, which is used as input for an Iterated Extended Kalman filter. We show that the proposed approach can achieve decimeter level accuracy in a simulation environment. Even with imperfect calibration, the total positioning error usually remains below 0.5 m. Positioning errors due to blocking of the receiver can be mitigated by employing an innovation magnitude bounds test. We also show that by employing multiple receivers, accuracy and robustness can be further improved.

Modulation waveform generators are frequently deployed for numerous applications such as communications. As a low-cost solution for high sampling rates, we investigate the BeagleBone Black (BBB) and more specific its Programmable Real-Time Unit (PRU) subsystem, which supports time critical tasks and fast deterministic IO operations. The implementation overview along with the achieved results in terms of throughput and reliability are herein presented and explained. The feasibility of a BBB PRU-based digital waveform generator was demonstrated under varying output configurations (up to 13) and sampling rates (up to 50 MSPS) with a high reliability .

In this paper, we study a Visible Light Positioning (VLP) system using Code Division Multiple Access (CDMA). In order to facilitate implementation, the LEDs are transmitting data in a non-synchronized way to the receiver requiring no backbone network. The positioning algorithm uses the received optical power calculated from the auto- correlation peak value. Because of the asynchronous system Multiple Access Interference (MAI), random interference with the auto- correlation peak, will occur and cause position errors. Practical results show that a CDMA VLP system can have position errors smaller then 40 cm and not be influenced by synchronization problems due to MAI. The positioning error and synchronization aren't only determined by the MAI but also the receiver Field Of View (FOV) is an important parameter. Depending on the CDMA code, the LEDs still have 97% of the illumination functionality compared when there is no communication.

Every year in Europe, about 1500 people die in traffic because they are not noticed by the truck driver. This problem could be solved by developing a wireless communication system where the truck driver and the cyclist are informed about each others presence. In this paper a test setup is presented in which the position of the cyclist is determined and displayed on a screen when being in the neighborhood of a truck. The cyclist gets an indication about notification by the truck. Because of the fast changing network, the cyclist must be added quickly to the network and the position must be updated very fast. For this reason a Zigbee communication system is used. The position of the cyclist is displayed in zones around the truck. The setup is experimentally tested and it is demonstrated that the proposed setup leads to a reliable and fast method to reduce the number of blind spot incidents.