Robots are controlled mechanisms, and their analysis and control requires adequately accurate but at the same time efficient models. While in the past, the computational efficacy of the kinematic and dynamic models were addressed, there is a recent interest in efficient and modular modeling procedur…

Promotionsvortrag

Exploitation of energy resources has been of interest to several governments around the world in recent years. Developments in shale gas extraction methods as well as the growing interest towards the use of geothermal energy triggered a collateral issue: earthquakes. Regions housing the energy sourc…

In 2016, Team Delft won the Amazon Robotics Challenge, a competition on autonomous manipulation. These competitions reveal the challenge in integrating complex robotic system architectures that need to perform complete tasks in real environments. Methods and tools are needed to build robotic system…

The talk is divided in two parts. In the first we introduce the notion of ontological analysis and foundational ontology and their role in knowledge organization and exploitation. In the second part, we look at how ontology can help artificial agents to achieve and manage commonsense/cognitive know…

In der vorliegenden kumulativen Dissertation werden das Design, die Implementierung, die Kontrolle und eine experimentelle Evaluation eines neuartigen Rovers mit aktivem Fahrwerk vorgenommen und beschrieben. Durch das hybride Fahrwerk wird eine Basis für vielfältige Lokomotionsformen geschaffen. Da…

This talk is given at a regular meeting of the task force ELLIAS (Embodied Lifelong Learning of Intelligent Autonomous Systems). I would like to use this opportunity to point out to everybody who is generally interested in machine learning and optimization (or everybody who participated in ELLIAS' …

PhD Talk: Learning Coordination and Reactivity of Movement Primitives from Demonstration Learning from human demonstrations is a promising way to teach complex motor systems novel skills in an intuitive manner without requiring robotic experts. This will be important for future robots cooperating w…

Deep learning has enabled traditional reinforcement learning methods to deal with high-dimensional problems. However, there have been several issues with deep reinforcement learning methods such as the limited exploration capability of learning agents, the ability to integrate human knowledge into l…

Made in China 2025 : strategic official government initiative to catch up with „western“ technology development and become a global leading force in dedicated industries (background, scope, current progress, chances & risks for China and partner countries). New silk road initiative (BRI : belt …