Die Verfügbarkeit qualitativ hochwertiger Daten über Unternehmensgrenzen hinweg ist eine Grundvoraussetzung für die Entwicklung fairer und zuverlässiger KI-basierter Systeme. Bestehende Datenökosysteme fokussieren jedoch primär den Austausch zwischen Unternehmen, während Endnutzende als Datenerzeugende weitgehend passive Akteure bleiben. Um Endnutzenden eine faire Datensouveränität zu ermöglichen, ergibt sich die Notwendigkeit neuer Ansätze. Dieses Paper untersucht, wie Governance-Mechanismen gestaltet werden müssen, um Datensouveränität, Datenverfügbarkeit, Transparenz und Nachvollziehbarkeit zu vereinen und somit aus Sicht von Corporate Digital Responsibility (CDR) verantwortungsvolle Systeme sicherzustellen. Basierend auf konzeptionellen Überlegungen zu dezentraler Datenhaltung und einer Analyse von Anwendungsfällen aus dem Bereich Smart Living wird ein Governance-Framework erarbeitet. Das Framework strukturiert zentrale Rollen, Prozesse und Mechanismen entlang des Datenlebenszyklus und ermöglicht eine systematische Bewertung hinsichtlich Umsetzbarkeit, Wirksamkeit und Beitrag zur Datenverfügbarkeit. Zudem werden praxisnahe Ansätze zur Umsetzung von Datensouveränität über reine regulatorische Mindestanforderungen der DSGVO hinaus aufgezeigt. Das Paper liefert damit einen Beitrag zu CDR für Datenökosysteme sowie zur Gestaltung fairer Datenakquise in KI-Kontexten.
Sensor-based Human Activity Recognition (HAR) underpins many ubiquitous and wearable computing applications, yet current models remain limited by scarce labels, sensor heterogeneity, and weak generalization across users, devices, and contexts. Foundation models, which are generally pretrained at scale using self-supervised and multimodal learning, offer a unifying paradigm to address these challenges by learning reusable, adaptable representations for activity understanding. This survey synthesizes emerging foundation models for sensor-based HAR. We first clarify foundational concepts, definitions, and evaluation criteria, then organize existing work using a lifecycle-oriented taxonomy spanning input design, pretraining, adaptation, and utilization. Rather than enumerating individual models, we analyze recurring design patterns and trade-offs across nine technical axes, including modality scope, tokenization, architectures, learning paradigms, adaptation mechanisms, and deployment settings. From this synthesis, we identify three dominant development trajectories: (1) HAR-specific foundation models trained from scratch on large sensor corpora, (2) adaptation of general time-series or multimodal foundation models to sensor-based HAR, and (3) integration of large language models for reasoning, annotation, and human-AI interaction. We conclude by highlighting open challenges in data curation, multimodal alignment, personalization, privacy, and responsible deployment, and outline directions toward general-purpose, interpretable, and human-centered foundation models for activity understanding. A complete, continuously updated index of papers and models is available in our companion repository: https://github.com/zhaxidele/Foundation-Models-Defining-A-New-Era-In-Human-Activity-Recognition.
In robotics, many different approaches ranging from classical planning over optimal control to reinforcement learning (RL) are developed and borrowed from other fields to achieve reliable control in diverse tasks. To get a clear understanding of their individual strengths and weaknesses and their applicability in real-world robotic scenarios, it is important to benchmark and compare their performances not only in a simulation but also on real hardware. The second AI Olympics with RealAIGym competition was held at the 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2024) to contribute to this cause and evaluate different controllers according to their ability to solve a dynamic control problem on an underactuated double-pendulum system (Figure 1) with chaotic dynamics. This article describes the four different RL methods submitted by the participating teams; presents their performance in the swing-up task on a real double pendulum, measured against various criteria; and discusses their transferability from simulation to real (sim-to-real) hardware and their robustness to external disturbances.
Object pose estimation is a fundamental problem in robotics and computer vision, yet it remains challenging due to partial observability, occlusions, and object symmetries, which inevitably lead to pose ambiguity and multiple hypotheses consistent with the same observation. While deterministic deep networks achieve impressive performance under well-constrained conditions, they are often overconfident and fail to capture the multi-modality of the underlying pose distribution. To address these challenges, we propose a probabilistic framework that leverages flow matching on the SE(3) manifold for estimating 6D object pose distributions. Unlike existing methods that regress a single deterministic output, our approach models the full pose distribution with a sample-based estimate and enables reasoning about uncertainty in ambiguous cases such as symmetric objects or severe occlusions. We achieve state-of-the-art results on Real275, YCB-V and LM-O, and demonstrate how our sample-based pose estimates can be leveraged in downstream robotic manipulation tasks such as active perception for disambiguating uncertain viewpoints, or guiding grasp synthesis in an uncertainty-aware manner.
Medical disease prediction, particularly through imaging, remains a challenging task due to the complexity and variability of medical data, including noise, ambiguity, and differing image quality. Recent deep learning models, including Knowledge Distillation (KD) methods, have shown promising results in brain tumor image identification but still face limitations in handling uncertainty and generalizing across diverse medical conditions. Traditional KD methods often rely on a context-unaware temperature parameter to soften teacher model predictions, which does not adapt effectively to varying uncertainty levels present in medical images. To address this issue, we propose a novel framework that integrates Ant Colony Optimization (ACO) for optimal teacher-student model selection and a novel context-aware predictor approach for temperature scaling. The proposed context-aware framework adjusts the temperature based on factors such as image quality, disease complexity, and teacher model confidence, allowing for more robust knowledge transfer. Additionally, red ACO is preferred for teacher-student model selection due to its efficiency in exploring complex solution spaces. It outperforms PSO and Grid Search by achieving 96.33% accuracy with only 47 evaluations, demonstrating faster convergence and lower computational cost. The proposed framework is evaluated using three publicly available benchmark datasets, each corresponding to a distinct medical imaging task. The results demonstrate that the proposed framework significantly outperforms current state-of-the-art methods, achieving top accuracy rates: 98.01% on the MRI brain tumor (Kaggle) dataset, 92.81% on the Figshare MRI dataset, and 96.20% on the GastroNet dataset. This enhanced performance represents a percentage increase of 0.77% over the existing benchmark of 97.24% (Kaggle), 1.38% over 91.43% (Figshare), and 1.20% over 95.00% (GastroNet).
