Learn More
There has been a recent focus in reinforcement learning on addressing continuous state and action problems by optimizing parame-terized policies. PI 2 is a recent example of this approach. It combines a derivation from first principles of stochastic optimal control with tools from statistical estimation theory. In this paper, we consider PI 2 as a member of(More)
One of the hallmarks of the performance, versatility , and robustness of biological motor control is the ability to adapt the impedance of the overall biomechanical system to different task requirements and stochastic disturbances. A transfer of this principle to robotics is desirable , for instance to enable robots to work robustly and safely in everyday(More)
Analysis and reconstruction of range images usually fo-cuses on complex objects completely contained in the field of view; little attention has been devoted so far to the reconstruction of partially occluded simple-shaped wide areas like parts of a wall hidden behind furniture pieces in an indoor range image. The work in this paper is aimed at such(More)
— One of the hallmarks of the performance, versatility, and robustness of biological motor control is the ability to adapt the impedance of the overall biomechanical system to different task requirements and stochastic disturbances. A transfer of this principle to robotics is desirable, for instance to enable robots to work robustly and safely in everyday(More)
—Temporal abstraction and task decomposition drastically reduce the search space for planning and control, and are fundamental to making complex tasks amenable to learning. In the context of reinforcement learning, temporal abstractions are studied within the paradigm of hierarchical reinforcement learning. We propose a hierarchical reinforcement learning(More)
— Segmenting complex movements into a sequence of primitives remains a difficult problem with many applications in the robotics and vision communities. In this work, we show how the movement segmentation problem can be reduced to a sequential movement recognition problem. To this end, we reformulate the original Dynamic Movement Primitive (DMP) formulation(More)
—For humans and robots, variable impedance control is an essential component for ensuring robust and safe physical interaction with the environment. Humans learn to adapt their impedance to specific tasks and environments; a capability which we continually develop and improve until we are well into our twenties. In this article, we reproduce functionally(More)
— This paper introduces the Assistive Kitchen as a comprehensive demonstration and challenge scenario for technical cognitive systems. We describe its hardware and software infrastructure. Within the Assistive Kitchen application, we select particular domain activities as research subjects and identify the cognitive capabilities needed for perceiving,(More)