A5012455464- Context-Aware Activity Recognition Systems
- Anomaly Detection Techniques and Applications
- Time Series Analysis and Forecasting
- IoT and Edge/Fog Computing
- Robotics and Sensor-Based Localization
- Robot Manipulation and Learning
- Bluetooth and Wireless Communication Technologies
- Business Process Modeling and Analysis
- Soft Robotics and Applications
- Flexible and Reconfigurable Manufacturing Systems
- Advanced Chemical Sensor Technologies
- Currency Recognition and Detection
- Service-Oriented Architecture and Web Services
- Advanced Software Engineering Methodologies
- Green IT and Sustainability
- Neural Networks and Applications
- Big Data and Business Intelligence
- Digital Transformation in Industry
TU Wien
2018-2021
Australian Centre for Robotic Vision
2020
We present an approach for safe, and object-independent human-to-robot handovers using real time robotic vision, manipulation. aim general applicability with a generic object detector, fast grasp selection algorithm, by single gripper-mounted RGB-D camera, hence not relying on external sensors. The robot is controlled via visual servoing towards the of interest. Putting high emphasis safety, we use two perception modules: human body part segmentation, hand/finger segmentation. Pixels that...
Context-awareness is becoming increasingly important as it allows to adapt the functionalities and user interfaces of applications based on environmental conditions or preferences. While contextual adaption already plays a significant role in areas like mobile consumer (B2C market), industrial domain still lacks proper discussion. This paper going define term context environment proposes framework for classification industry-specific types. Using this framework, most common contexts are...
Today, most IoT solutions for the production ecosystem stem from trends that first established at consumer market. Although these concepts have been adapted well in industrial environment, it led to fragmented require complex interfaces. With recent introduction of GAIA-X, becomes possible develop platform independent tailored needs manufacturers. Until now, GAIA-X is only a concept proposed by governments and economic advisory boards. This paper extends into an system architecture enables...
New developments in domains like mathematics and statistical learning availability of easy-to-use, often freely accessible software tools offer great potential to transform the manufacturing domain their grasp on increased data repositories sustainably. One most exciting is area machine learning. Time series clustering could be utilized state detection which can used predictive maintenance or online optimization. This paper presents a comparison available time algorithms, by applying several...
The availability of precise sensors and the extensive usage smart devices enable development systems that can sense their environment recognize specific contexts. In recent years, so-called context-aware gained increasing popularity as they provide situational assistance automate nondeterministic processes. Despite advantages, these still play a minor role in industrial applications due to reasons such increased efforts required for engineering process absence methods handle inherent...
Industrial edge devices starting to play a major role as API gateway for data consumers or cloud applications. To fulfill this task industrial are mostly build from single board computer small computers with an operation system. Considering the increasing processing power of these there is room applications that enable preparation on shop floor. This paper proposes lightweight approach structure SAX Algorithm and add semantic information's dataset. Additionally, example using machine...
The usage of smart devices in combination with the extensive deployment sensors enables development systems that can recognize their environment and act accordingly. These so-called context-aware allow automation user interactions by providing desired functionality based on an understanding users' current context. During such systems, context-related system properties, contextual functionalities, as well underlying contexts must be defined. UML models are a valuable tool for tasks. In this...