Related papers: Online Open World Recognition

Identifying the dynamic properties of manipulated objects is essential for safe and accurate robot control. Most methods rely on low noise force torque sensors, long exciting signals, and solving nonlinear optimization problems, making the…

While recent work on online goal recognition efficiently infers goals under low observability, comparatively less work focuses on online goal recognition that works in both discrete and continuous domains. Online goal recognition approaches…

In recent years, the performance of action recognition has been significantly improved with the help of deep neural networks. Most of the existing action recognition works hold the \textit{closed-set} assumption that all action categories…

To aid humans in everyday tasks, robots need to know which objects exist in the scene, where they are, and how to grasp and manipulate them in different situations. Therefore, object recognition and grasping are two key functionalities for…

The capability of predicting environmental dynamics underpins both biological neural systems and general embodied AI in adapting to their surroundings. Yet prevailing approaches rest on static world models that falter when confronted with…

Recent advances in Internet-of-Things (IoT) technologies have sparked significant interest towards developing learning-based sensing applications on embedded edge devices. These efforts, however, are being challenged by the complexities of…

Driven by advancements in deep learning, computer-aided diagnoses have made remarkable progress. However, outside controlled laboratory settings, algorithms may encounter several challenges. In the medical domain, these difficulties often…

A characteristic of existing predictive process monitoring techniques is to first construct a predictive model based on past process executions, and then use it to predict the future of new ongoing cases, without the possibility of updating…

For many real-world robotics applications, robots need to continually adapt and learn new concepts. Further, robots need to learn through limited data because of scarcity of labeled data in the real-world environments. To this end, my…

We revisit the online dynamic acknowledgment problem. In the problem, a sequence of requests arrive over time to be acknowledged, and all outstanding requests can be satisfied simultaneously by one acknowledgement. The goal of the problem…

Segmenting object parts such as cup handles and animal bodies is important in many real-world applications but requires more annotation effort. The largest dataset nowadays contains merely two hundred object categories, implying the…

In contrast to the incremental classification task, the incremental detection task is characterized by the presence of data ambiguity, as an image may have differently labeled bounding boxes across multiple continuous learning stages. This…

Traditional supervised learning makes the closed-world assumption that the classes appeared in the test data must have appeared in training. This also applies to text learning or text classification. As learning is used increasingly in…

Models trained for classification often assume that all testing classes are known while training. As a result, when presented with an unknown class during testing, such closed-set assumption forces the model to classify it as one of the…

Continual learning is essential for all real-world applications, as frozen pre-trained models cannot effectively deal with non-stationary data distributions. The purpose of this study is to review the state-of-the-art methods that allow…

while most of the tactile robots are operated in close-set conditions, it is challenging for them to operate in open-set conditions where test objects are beyond the robots' knowledge. We proposed an open-set recognition framework using…

In a real-world setting, object instances from new classes can be continuously encountered by object detectors. When existing object detectors are applied to such scenarios, their performance on old classes deteriorates significantly. A few…

In this thesis, we draw inspiration from both classical system identification and modern machine learning in order to solve estimation problems for real-world, physical systems. The main approach to estimation and learning adopted is…

Vision systems mounted on home robots need to interact with unseen classes in changing environments. Robots have limited computational resources, labelled data and storage capability. These requirements pose some unique challenges: models…

Modeling dynamical systems is important in many disciplines, e.g., control, robotics, or neurotechnology. Commonly the state of these systems is not directly observed, but only available through noisy and potentially high-dimensional…