The dynamics of deformable objects, especially that of highly flexible articles of clothing, is difficult to model. This is due to their vast number of degrees of freedom in addition to the noisy and incomplete measurements robots have to cope with. Therefore, we suggest focusing on the structures and object parts which are relevant to the task at hand. The openings (e.g., at the waist, leg or sleeve ends) characterize garments surprisingly well, not only from a topological perspective, but also in terms of their inherent function, namely dressing. We model openings as closed, oriented chains of movable points which we refer to as Active Boundary Component Models (ABCMs). Compared with the hardly predictable motions of an overall piece of clothing, relatively strict assumptions regarding the dynamics of these contour models can be made. We express these assumptions through position-based constraints which drastically restrict the degrees of freedom. In the present paper, we show how ABCMs can be initialized exploiting geometric prior knowledge of garments, and how they can be tracked visually using 3D point cloud data. Additionally, we consider the task of sliding a rod through a pant leg as a first step toward robotic dressing assistance for physically handicapped persons.

Identifying the relevant functional degrees of freedom is a key prerequisite for the proper handling of everyday objects. Recognizing and exploiting these degrees of freedom in the context of non-rigid objects poses challenges that are significantly different from the rigid case. As a major generic subtask, we consider the identification and exploitation of boundary components during clothes manipulation, combining RGBD vision with uni- and bi-manual handling through a robot. Specifically, we present a novel graph-based approach to detecting boundary components by extracting closed contours from depth images. Based on that, we suggest a planner minimizing a heuristic energy function for an optimal grasp pose of a robot hand around the boundary of a garment. We demonstrate the effectiveness of the approach in interactive perception and regrasping experiments with a dual arm and two attached anthropomorphic hands. Furthermore, we show how to make use of these capabilities to implement a basic skill for a coat-check robot: hanging up a knit cap on a hat-stand.

Eye movements play an essential role in planning and executing manual actions. Eye-hand coordination is a natural human skill. We exploit this skill for an intuitive remote manipulation system that allows even non-expert users to operate a robot safely without prior experience. Specifically, we propose a visio-haptic approach to controlling a 7-DOF robotic arm. Our system is fully mobile, allowing for unconstraint operation in any environment. An eyetracker captures the operator's gaze. The end effector or particular joints are selected by simply fixating the to-be-controlled segment. A sensor-equipped tangible object provides a haptic interface between the operator's hand and the focused part of the robotic arm. The system features two operation modes, direct joint rotation and 3d end effector control in a global cartesian frame. We evaluated the system in a proof-of-concept study with untrained users. The participants safely operated the robot and accomplished an obstacle avoidance task. For this purpose, they used both operation modes.

Mobile robots that are employed in people's homes need to safely navigate their environment. And natural human-inhabited environments still pose significant challenges for robots despite the impressive progress that has been achieved in the field of path planning and obstacle avoidance. These challenges mostly arise from the fact that (i) the perceptual abilities of a robot are limited, thus sometimes impeding its ability to see relevant obstacles (e.g. transparent objects), and (ii) the environment is highly dynamic being populated by humans. In this contribution we are making a case for an integrated solution to these challenges that builds upon the analysis and use of implicit human knowledge in path planning and a cascade of replanning approaches. We combine state of the art path planning and obstacle avoidance algorithms with the knowledge about how humans navigate in their very own environment. The approach results in a more robust and predictable navigation ability for domestic robots as is demonstrated in a number of experimental runs.