Michael Feld
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Michael Feld has a total of 58 co-authors. Here are the top co-authors by number of shared publications:
- Niko Kleer
DFKI, Saarland University
6 shared publications - Amr Gomaa
German Research Center for Artificial Intelligence
4 shared publications - Amr Gomaa
Https github.com/microsoft/Firewalled-Agentic-Networks
3 shared publications - Antonio Krüger
Saarland University, Saarbrücken, Germany and DFKI, Saarbrücken, Germany
3 shared publications - Guillermo Reyes
German Research Center for Artificial Intelligence (DFKI), Germany
2 shared publications - Irene Georgakoudi
Tufts Unive
2 shared publications
Latest Publications
- Open Access
- 10 June 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Interactive Intelligent Systems
- Vol. 16 (3) , 1-20
Looking for an even better fit? A Personalized Incremental Reinforcement Learning Multimodal Object Referencing Framework
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 proposed, in our previous work, an incremental learning approach, adapting to changing user behavior. Although this method proved superior over state-of-the-art approaches, it still lacked in performance and had some computational resource limitations, mainly the small-sized memory needed to store a subset of old data for incremental learning. Therefore, in this work, we propose an alternative solution using reinforcement learning that can be used to overcome memory storage limitations, achieving a zero data storage approach for incremental learning without performance loss. Our newly enhanced solution has been added to our previous framework at https://github.com/amrgomaaelhady/IcRegress .
- 10 June 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Interactive Intelligent Systems
- Vol. 16 (3) , 1-20
Open AccessLooking for an even better fit? A Personalized Incremental Reinforcement Learning Multimodal Object Referencing Framework
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 proposed, in our previous work, an incremental learning approach, adapting to changing user behavior. Although this method proved superior over state-of-the-art approaches, it still lacked in performance and had some computational resource limitations, mainly the small-sized memory needed to store a subset of old data for incremental learning. Therefore, in this work, we propose an alternative solution using reinforcement learning that can be used to overcome memory storage limitations, achieving a zero data storage approach for incremental learning without performance loss. Our newly enhanced solution has been added to our previous framework at https://github.com/amrgomaaelhady/IcRegress .
- Open Access
- 30 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 653-658
Identification of Important LLM Test Criteria for State Media Authorities
- 30 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 653-658
Open AccessIdentification of Important LLM Test Criteria for State Media Authorities
- Open Access
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.
Open AccessYour 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.
- 27 August 2024
- Published by Springer Nature
- p. 288-299
Capturing Task-Related Information for Text-Based Grasp Classification Using Fine-Tuned Embeddings
- 27 August 2024
- Published by Springer Nature
- p. 288-299
Capturing Task-Related Information for Text-Based Grasp Classification Using Fine-Tuned Embeddings
- 27 August 2024
- Published by Springer Nature
- p. 300-312
StepDP: A Step Towards Expressive and Pervasive Dialogue Platforms
- 27 August 2024
- Published by Springer Nature
- p. 300-312
StepDP: A Step Towards Expressive and Pervasive Dialogue Platforms
- Open Access
- 18 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-13
Looking for a better fit? An Incremental Learning Multimodal Object Referencing Framework adapting to Individual Drivers
- 18 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-13
Open AccessLooking for a better fit? An Incremental Learning Multimodal Object Referencing Framework adapting to Individual Drivers
- Open Access
- 11 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 613-617
Towards Remote Expert Supported Autonomous Assistant Robots in Shopping Environments
Autonomous robots that assist customers during their shopping trips may become ubiquitous in the near future. However, these systems are limited in their ability to appropriately reply to all of a customer's requests. Therefore, a dedicated human expert has to remotely "take over" and resolve the customer's issue to warrant a satisfying experience. As a result, a Transfer of Control from a machine to a human takes place. This creates the problem that the expert needs to quickly review what has happened prior to the take-over to provide optimal assistance. To address this, we designed and implemented an interactive summary concept allowing experts to quickly filter and review the most relevant information to solve the given issue. Finally, we provide an example use case illustrating how a remote expert may solve a request using our system.
- 11 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 613-617
Open AccessTowards Remote Expert Supported Autonomous Assistant Robots in Shopping Environments
Autonomous robots that assist customers during their shopping trips may become ubiquitous in the near future. However, these systems are limited in their ability to appropriately reply to all of a customer's requests. Therefore, a dedicated human expert has to remotely "take over" and resolve the customer's issue to warrant a satisfying experience. As a result, a Transfer of Control from a machine to a human takes place. This creates the problem that the expert needs to quickly review what has happened prior to the take-over to provide optimal assistance. To address this, we designed and implemented an interactive summary concept allowing experts to quickly filter and review the most relevant information to solve the given issue. Finally, we provide an example use case illustrating how a remote expert may solve a request using our system.
- Open Access
- 9 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 689-694
Towards Adaptive User-centered Neuro-symbolic Learning for Multimodal Interaction with Autonomous Systems
- 9 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 689-694
Open AccessTowards Adaptive User-centered Neuro-symbolic Learning for Multimodal Interaction with Autonomous Systems
- Open Access
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.
Open AccessIt'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.
- Open Access
- 18 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 234-243
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.
- 18 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 234-243
Open AccessIt’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.