arXiv subjects

Michael Feld

Publications and source records attributed to Michael Feld.

14 recordsLinked to original sources

arXiv2025

Your Interface, Your Control: Adapting Takeover Requests for Seamless Handover in Semi-Autonomous Vehicles

With the automotive industry transitioning towards conditionally automated driving, takeover warning systems are crucial for ensuring safe collaborative driving between users and semi-automated vehicles. However, previous work has focused on static warning systems that do not accommodate different driver states. Therefore, we propose an adaptive takeover warning system that is personalised to drivers, enhancing their experience and safety. We conducted two user studies investigating semi-autonomous driving scenarios in rural and urban environments while participants performed non-driving-related tasks such as text entry and visual search. We investigated the effects of varying time budgets and head-up versus head-down displays for takeover requests on drivers' situational awareness and mental state. Through our statistical and clustering analyses, we propose strategies for designing adaptable takeover systems, e.g., using longer time budgets and head-up displays for non-hazardous takeover events in high-complexity environments while using shorter time budgets and head-down displays for hazardous events in low-complexity environments.

cs.HC↗

arXiv2024

Looking for a better fit? An Incremental Learning Multimodal Object Referencing Framework adapting to Individual Drivers

The rapid advancement of the automotive industry towards automated and semi-automated vehicles has rendered traditional methods of vehicle interaction, such as touch-based and voice command systems, inadequate for a widening range of non-driving related tasks, such as referencing objects outside of the vehicle. Consequently, research has shifted toward gestural input (e.g., hand, gaze, and head pose gestures) as a more suitable mode of interaction during driving. However, due to the dynamic nature of driving and individual variation, there are significant differences in drivers' gestural input performance. While, in theory, this inherent variability could be moderated by substantial data-driven machine learning models, prevalent methodologies lean towards constrained, single-instance trained models for object referencing. These models show a limited capacity to continuously adapt to the divergent behaviors of individual drivers and the variety of driving scenarios. To address this, we propose \textit{IcRegress}, a novel regression-based incremental learning approach that adapts to changing behavior and the unique characteristics of drivers engaged in the dual task of driving and referencing objects. We suggest a more personalized and adaptable solution for multimodal gestural interfaces, employing continuous lifelong learning to enhance driver experience, safety, and convenience. Our approach was evaluated using an outside-the-vehicle object referencing use case, highlighting the superiority of the incremental learning models adapted over a single trained model across various driver traits such as handedness, driving experience, and numerous driving conditions. Finally, to facilitate reproducibility, ease deployment, and promote further research, we offer our approach as an open-source framework at \url{https://github.com/amrgomaaelhady/IcRegress}.

cs.HC↗

arXiv2023

It's all about you: Personalized in-Vehicle Gesture Recognition with a Time-of-Flight Camera

Despite significant advances in gesture recognition technology, recognizing gestures in a driving environment remains challenging due to limited and costly data and its dynamic, ever-changing nature. In this work, we propose a model-adaptation approach to personalize the training of a CNNLSTM model and improve recognition accuracy while reducing data requirements. Our approach contributes to the field of dynamic hand gesture recognition while driving by providing a more efficient and accurate method that can be customized for individual users, ultimately enhancing the safety and convenience of in-vehicle interactions, as well as driver's experience and system trust. We incorporate hardware enhancement using a time-of-flight camera and algorithmic enhancement through data augmentation, personalized adaptation, and incremental learning techniques. We evaluate the performance of our approach in terms of recognition accuracy, achieving up to 90\%, and show the effectiveness of personalized adaptation and incremental learning for a user-centered design.

cs.CV↗

arXiv2023

Adaptive User-centered Neuro-symbolic Learning for Multimodal Interaction with Autonomous Systems

Recent advances in machine learning, particularly deep learning, have enabled autonomous systems to perceive and comprehend objects and their environments in a perceptual subsymbolic manner. These systems can now perform object detection, sensor data fusion, and language understanding tasks. However, there is a growing need to enhance these systems to understand objects and their environments more conceptually and symbolically. It is essential to consider both the explicit teaching provided by humans (e.g., describing a situation or explaining how to act) and the implicit teaching obtained by observing human behavior (e.g., through the system's sensors) to achieve this level of powerful artificial intelligence. Thus, the system must be designed with multimodal input and output capabilities to support implicit and explicit interaction models. In this position paper, we argue for considering both types of inputs, as well as human-in-the-loop and incremental learning techniques, for advancing the field of artificial intelligence and enabling autonomous systems to learn like humans. We propose several hypotheses and design guidelines and highlight a use case from related work to achieve this goal.

cs.AI↗

arXiv2023

Teach Me How to Learn: A Perspective Review towards User-centered Neuro-symbolic Learning for Robotic Surgical Systems

Recent advances in machine learning models allowed robots to identify objects on a perceptual nonsymbolic level (e.g., through sensor fusion and natural language understanding). However, these primarily black-box learning models still lack interpretation and transferability and require high data and computational demand. An alternative solution is to teach a robot on both perceptual nonsymbolic and conceptual symbolic levels through hybrid neurosymbolic learning approaches with expert feedback (i.e., human-in-the-loop learning). This work proposes a concept for this user-centered hybrid learning paradigm that focuses on robotic surgical situations. While most recent research focused on hybrid learning for non-robotic and some generic robotic domains, little work focuses on surgical robotics. We survey this related research while focusing on human-in-the-loop surgical robotic systems. This evaluation highlights the most prominent solutions for autonomous surgical robots and the challenges surgeons face when interacting with these systems. Finally, we envision possible ways to address these challenges using online apprenticeship learning based on implicit and explicit feedback from expert surgeons.

cs.RO↗

arXiv2021

ML-PersRef: A Machine Learning-based Personalized Multimodal Fusion Approach for Referencing Outside Objects From a Moving Vehicle

Over the past decades, the addition of hundreds of sensors to modern vehicles has led to an exponential increase in their capabilities. This allows for novel approaches to interaction with the vehicle that go beyond traditional touch-based and voice command approaches, such as emotion recognition, head rotation, eye gaze, and pointing gestures. Although gaze and pointing gestures have been used before for referencing objects inside and outside vehicles, the multimodal interaction and fusion of these gestures have so far not been extensively studied. We propose a novel learning-based multimodal fusion approach for referencing outside-the-vehicle objects while maintaining a long driving route in a simulated environment. The proposed multimodal approaches outperform single-modality approaches in multiple aspects and conditions. Moreover, we also demonstrate possible ways to exploit behavioral differences between users when completing the referencing task to realize an adaptable personalized system for each driver. We propose a personalization technique based on the transfer-of-learning concept for exceedingly small data sizes to enhance prediction and adapt to individualistic referencing behavior. Our code is publicly available at https://github.com/amr-gomaa/ML-PersRef.

cs.HC↗

arXiv2021

Multimodal Fusion Using Deep Learning Applied to Driver's Referencing of Outside-Vehicle Objects

There is a growing interest in more intelligent natural user interaction with the car. Hand gestures and speech are already being applied for driver-car interaction. Moreover, multimodal approaches are also showing promise in the automotive industry. In this paper, we utilize deep learning for a multimodal fusion network for referencing objects outside the vehicle. We use features from gaze, head pose and finger pointing simultaneously to precisely predict the referenced objects in different car poses. We demonstrate the practical limitations of each modality when used for a natural form of referencing, specifically inside the car. As evident from our results, we overcome the modality specific limitations, to a large extent, by the addition of other modalities. This work highlights the importance of multimodal sensing, especially when moving towards natural user interaction. Furthermore, our user based analysis shows noteworthy differences in recognition of user behavior depending upon the vehicle pose.

cs.HC↗

arXiv2020

You Have a Point There: Object Selection Inside an Automobile Using Gaze, Head Pose and Finger Pointing

Sophisticated user interaction in the automotive industry is a fast emerging topic. Mid-air gestures and speech already have numerous applications for driver-car interaction. Additionally, multimodal approaches are being developed to leverage the use of multiple sensors for added advantages. In this paper, we propose a fast and practical multimodal fusion method based on machine learning for the selection of various control modules in an automotive vehicle. The modalities taken into account are gaze, head pose and finger pointing gesture. Speech is used only as a trigger for fusion. Single modality has previously been used numerous times for recognition of the user's pointing direction. We, however, demonstrate how multiple inputs can be fused together to enhance the recognition performance. Furthermore, we compare different deep neural network architectures against conventional Machine Learning methods, namely Support Vector Regression and Random Forests, and show the enhancements in the pointing direction accuracy using deep learning. The results suggest a great potential for the use of multimodal inputs that can be applied to more use cases in the vehicle.

cs.HC↗

arXiv2020

Studying Person-Specific Pointing and Gaze Behavior for Multimodal Referencing of Outside Objects from a Moving Vehicle

Hand pointing and eye gaze have been extensively investigated in automotive applications for object selection and referencing. Despite significant advances, existing outside-the-vehicle referencing methods consider these modalities separately. Moreover, existing multimodal referencing methods focus on a static situation, whereas the situation in a moving vehicle is highly dynamic and subject to safety-critical constraints. In this paper, we investigate the specific characteristics of each modality and the interaction between them when used in the task of referencing outside objects (e.g. buildings) from the vehicle. We furthermore explore person-specific differences in this interaction by analyzing individuals' performance for pointing and gaze patterns, along with their effect on the driving task. Our statistical analysis shows significant differences in individual behaviour based on object's location (i.e. driver's right side vs. left side), object's surroundings, driving mode (i.e. autonomous vs. normal driving) as well as pointing and gaze duration, laying the foundation for a user-adaptive approach.

cs.HC↗

arXiv2012

Radio frequency spectra of Feshbach molecules in quasi-two dimensional geometries

The line shape of radio frequency spectra of tightly bound Feshbach molecules in strong transverse confinement can be described by a simple analytic formula that includes final state interactions. By direct comparison to experimental data, we clarify the role of effective range corrections to two-body bound-state energies in lower dimensions.

cond-mat.quant-gas↗

arXiv2012

Attractive and repulsive Fermi polarons in two dimensions

The dynamics of a single impurity in an environment is a fundamental problem in many-body physics. In the solid state, a well-known case is an impurity coupled to a bosonic bath, for example lattice vibrations. Here the impurity together with its accompanying lattice distortion form a new entity, a polaron. This quasiparticle plays an important role in the spectral function of high-Tc superconductors as well as in colossal-magnetoresistance in manganites. For impurities in a fermionic bath, the attention so far has been mostly on heavy or immobile impurities which exhibit Anderson's orthogonality catastrophe and the Kondo effect. Only recently, mobile impurities have moved into the focus of research and they have been found to form new quasiparticles, so called Fermi polarons. The Fermi polaron problem constitutes the extreme, but conceptually simple, limit of two important quantum many-body problems: the BEC-BCS crossover with spin-imbalance for attractive interactions and Stoner's itinerant ferromagnetism for repulsive interactions. It has been proposed that this and other yet elusive exotic quantum phases might become realizable in Fermi gases confined to two dimensions. Their stability and observability is intimately related to the theoretically debated properties of the Fermi polaron in two dimensional Fermi gas. Here we create and investigate these Fermi polarons and measure their spectral function using momentum-resolved photoemission spectroscopy. For attractive interactions we find evidence for the disputed pairing transition between polarons and tightly bound dimers, which provides insight into the elementary pairing mechanism of imbalanced, strongly-coupled two-dimensional Fermi gases. Additionally, for repulsive interactions we study novel quasiparticles, repulsive polarons, whose lifetime determine the possibility of stabilizing repulsively interacting Fermi systems.

cond-mat.quant-gas↗

arXiv2011

Scale invariance and viscosity of a two-dimensional Fermi gas

We investigate the collective excitations of a harmonically trapped two-dimensional Fermi gas from the collisionless (zero sound) to the hydrodynamic (first sound) regime. The breathing mode, which is sensitive to the equation of state, is observed at a frequency two times the dipole mode frequency for a large range of interaction strengths and temperatures, and the amplitude of the breathing mode is undamped. This provides evidence for a dynamical SO(2,1) scaling symmetry of the two-dimensional Fermi gas. Moreover, we investigate the quadrupole mode to measure the shear viscosity of the two-dimensional gas and study its temperature dependence.

cond-mat.quant-gas↗

arXiv2011

Observation of a pairing pseudogap in a two-dimensional Fermi gas

Pairing of fermions is ubiquitous in nature and it is responsible for a large variety of fascinating phenomena like superconductivity, superfluidity of $^3$He, the anomalous rotation of neutron stars, and the BEC-BCS crossover in strongly interacting Fermi gases. When confined to two dimensions, interacting many-body systems bear even more subtle effects, many of which lack understanding at a fundamental level. Most striking is the, yet unexplained, effect of high-temperature superconductivity in cuprates, which is intimately related to the two-dimensional geometry of the crystal structure. In particular, the questions how many-body pairing is established at high temperature and whether it precedes superconductivity are crucial to be answered. Here, we report on the observation of pairing in a harmonically trapped two-dimensional atomic Fermi gas in the regime of strong coupling. We perform momentum-resolved photoemission spectroscopy, analogous to ARPES in the solid state, to measure the spectral function of the gas and we detect a many-body pairing gap above the superfluid transition temperature. Our observations mark a significant step in the emulation of layered two-dimensional strongly correlated superconductors using ultracold atomic gases.

cond-mat.quant-gas↗

arXiv2010

Radiofrequency spectroscopy of a strongly interacting two-dimensional Fermi gas

We realize and study a strongly interacting two-component atomic Fermi gas confined to two dimensions in an optical lattice. Using radio-frequency spectroscopy we measure the interaction energy of the strongly interacting gas. We observe the confinement-induced Feshbach resonance and find the existence of confinement-induced molecules in very good agreement with theoretical predictions.

cond-mat.quant-gas↗