Laser Feedback Interferometry (LFI) enables eye tracking from scalar optical path length (OPL) measurements rather than image features used in video oculography (VOG). While LFI allows compact, low-power, and ambient-light-robust sensing, it renders conventional image-based gaze estimation methods inapplicable. Instead, gaze must be inferred from sparse scalar measurements, leading to a highly non-linear and ambiguous inverse problem due to corneal refraction.

Smart glasses, including audio, augmented reality, and auto focal glasses, are emerging as a new class of wearables, designed to enhance user interaction with surroundings. Despite their potential, smart glasses suffer from limited natural interaction methods. Gaze tracking offers a promising solution, allowing users to interact with the device and their surroundings using their eyes. However, current video oculography (VOG) systems face challenges such as high-power consumption, bulky sensors, and reduced robustness in varying lighting conditions. To address these issues, we propose Laser Feedback Interferometry (LFI) sensors as an alternative to VOG. LFI sensors offer advantages in size, power efficiency, and ambient light robustness. The proposed LFI eye-tracking sensor integrates seamlessly into lightweight eye wear, requiring no user-specific calibration and enabling continuous, all-day use. To ensure reliable tracking across a wide range of users with varying interpupillary distances, we employ elongated laser beams that cover a broader eye region. This design enhances tracking precision by accurately capturing the user's gaze vector while maintaining robustness under different lighting conditions. We developed a comprehensive simulation model that integrates the sensor and eye model, validated against real-world experiments, and designed a convolutional neural network (CNN) based model to accurately estimate gaze from LFI sensor readings. Our results demonstrate that the LFI-based system provides a robust, efficient, and user-friendly gaze interaction solution, achieving high gaze prediction accuracy with an error margin of 2.23° on a custom simulation dataset. This represents a significant step toward next-generation smart glasses.

This paper is about a small eye tracking study for scan path classification. Seven participants played Mario Kart while wearing a head mounted eye tracker. In total, we had 64 recordings, but one had to be removed (Only 79 gaze samples were recorded). We compared different scan path classification features to estimate the performance of the participants based on the ranking they achieved. The best performing feature was ENCODJI which incooperates saccades and the heatmap in one feature. HOV, which uses saccade angles, performed well for all tasks but was outperformed by the heatmap (HEAT) for the last two groups.

Eye-tracking is a key sensing technology for upcoming retinal projection augmented reality (AR) glasses. State-of-the-art eye-tracking sensor technologies rely on video oculography (VOG) and 3D model based gaze estimation algorithms, which infer gaze from observations of the projected pupil over time. The convergence time of these algorithms relies heavily on the pupil ellipse fitting accuracy. In this work, we investigate the effects of pupil ellipse contour noise and pupil center noise on the convergence time of a state-of-the-art eye-tracking approach and show that the convergence time relies heavily on a sub-pixel accurate pupil ellipse fitting and can reach tens of seconds for inaccurately fitted ellipses.

Eye-tracking is a key technology for future retinal projection based AR glasses as it enables techniques such as foveated rendering or gaze-driven exit pupil steering, which both increases the system’s overall performance. However, two of the major challenges video oculography systems face are robust gaze estimation in the presence of glasses slippage, paired with the necessity of frequent sensor calibration. To overcome these challenges, we propose a novel, calibration-free eye-tracking sensor for AR glasses based on a highly transparent holographic optical element (HOE) and a laser scanner. We fabricate a segmented HOE generating two stereo images of the eye-region. A single-pixel detector in combination with our stereo reconstruction algorithm is used to precisely calculate the gaze position. In our laboratory setup we demonstrate a calibration-free accuracy of 1.35° achieved by our eye-tracking sensor; highlighting the sensor’s suitability for consumer AR glasses.

After the success of smartphones and smartwatches, smart glasses are expected to be the next smart wearable. While novel display technology allows the seamlessly embedding of content into the FOV, interaction methods with glasses, requiring the user for active interaction, limiting the user experience. One way to improve this and drive immersive augmentation is to reduce user interactions to a necessary minimum by adding context awareness to smart glasses. For this, we propose an approach based on human activity recognition, which incorporates features, derived from the user's head- and eye-movement. Towards this goal, we combine an commercial eye-tracker and an IMU to capture eye- and head-movement features of 7 activities performed by 20 participants. From a methodological perspective, we introduce U-HAR, a convolutional network optimized for activity recognition. By applying a few-shot learning, our model reaches an macro-F1-score of 86.59%, allowing us to derive contextual information.

Robust and highly integrated eye-tracking is a key technology to improve resolution of near-eye-display technologies for augmented reality (AR) glasses such as focus-free retinal projection as it enables display enhancements like foveated rendering. Furthermore, eye-tracking sensors enables novel ways to interact with user interfaces of AR glasses, improving thus the user experience compared to other wearables. In this work, we present a novel approach to track the user's eye by scanned laser feedback interferometry sensing. The main advantages over modern video-oculography (VOG) systems are the seamless integration of the eye-tracking sensor and the excellent robustness to ambient light with significantly lower power consumption. We further present an algorithm to track the bright pupil signal captured by our sensor with a significantly lower computational effort compared to VOG systems. We evaluate a prototype to prove the high robustness against ambient light and achieve a gaze accuracy of 1.62\,$^\circ$, which is comparable to other state-of-the-art scanned laser eye-tracking sensors. The outstanding robustness and high integrability of the proposed sensor will pave the way for everyday eye-tracking in consumer AR glasses.

The Internet of Things and Wireless Sensor Nodes are spreading into more and more homes and offices. Current wireless sensor systems rely on the use of batteries. Since batteries are made from scarce resources and have to be exchanged regularly their use is not optimal. To avoid these limitations energy harvesting is a possible alternative. Currently most energy harvesting based sensor nodes use simple low energy sensors. To expand the possibility of energy harvesting this paper presents a sensor node using a geomagnetic sensor, which normally is used in battery or mains powered devices.

This work presents a new approach to estimate the orientation of wireless sensor nodes (WSN) using geomagnetic sensors. The main contribution is a new algorithm for supervised orientation estimation using geomagnetic fingerprinting. Combined with hierarchical sensing our approach leads to a significant reduction of power consumption.

Energy neutral computing is seen as a design approach for wireless sensor nodes (WSN) which are powered by energy harvesters. The approach relies on keeping an equilibrium between consumption and harvesting of energy and typically uses models for energy prediction and management. To adapt models to specific systems and environments, often characterization measurements are used. Measurements strongly influence the model quality and with this the usability of such WSN. In this paper a novel measurement system (PiEMS) is presented that outperforms existing approaches and helps to optimize typical characterization tasks. The increased accuracy of characterization and modeling are exemplified for different WSN applications.

A System of Cyber-Physical Systems (SoCPS) is a sensible combination of individual cyber-physical systems (CPS) to realise new functions digitalised and exposed as services in the internet. The Industry 4.0 concept also pursues this approach and thus realises flexible and individual production by implementing new functions on the shop floor and intelligently linking production lines. Due to this increased flexibility, environmental influences during the production process are becoming increasingly important. This work proposes an approach to integrate the influence of environmental parameters in relation to the behaviour of SoCPS. For this, the general use of environmental parameters with SoCPS is shown with their significance for Industry 4.0-compliant solutions. Furthermore, it will present how the environmental parameters can be measured and used by means of a cyber-physical sensor system developed and implemented conforming to RAMI4.0 specifications.