In this paper we describe a system for aerial manipulation composed of a helicopter platform and a fully actuated seven Degree of Freedom (DoF) redundant industrial robotic arm. We present the first analysis of such kind of systems and show that the dynamic coupling between helicopter and arm can generate diverging oscillations with very slow frequency which we called phase circles. Based on the presented analysis, we propose a control approach for the whole system. The partial decoupling between helicopter and arm-which eliminates the phase circles-is achieved by means of special movement of robotic arm utilizing its redundant DoF. For the underlying arm control a specially designed impedance controller was proposed. In different flight experiments we showcase that the proposed kind of system type might be used in the future for practically relevant tasks. In an integrated experiment we demonstrate a basic manipulation task-impedance based grasping of an object from the environment underlaying a visual object tracking control loop.

Objective: Currently, there are some 95,000 people in Europe suffering from upper-limb impairment. Rehabilitation should be undertaken right after the impairment occurs and should be regularly performed thereafter. Moreover, the rehabilitation process should be tailored specifically to both patient and impairment. Approach: To address this, we have developed a low-cost solution that integrates an off-the-shelf Virtual Reality (VR) setup with our in-house developed arm/hand intent detection system. The resulting system, called VITA, enables an upper-limb disabled person to interact in a virtual world as if her impaired limb were still functional. VITA provides two specific features that we deem essential: proportionality of force control and interactivity between the user and the intent detection core. The usage of relatively cheap commercial components enable VITA to be used in rehabilitation centers, hospitals, or even at home. The applications of VITA range from rehabilitation of patients with musculodegenerative conditions (e.g. ALS), to treating phantom-limb pain of people with limb-loss and prosthetic training. Main Results: We present a multifunctional system for upper-limb rehabilitation in VR. We tested the system using a VR implementation of a standard hand assessment tool, the Box and Block test and performed a user study on this standard test with both intact subjects and a prosthetic user. Furthermore, we present additional applications, showing the versatility of the system. Significance: The VITA system shows the applicability of a combination of our experience in intent detection with state-of-the art VR system for rehabilitation purposes. With VITA, we have an all-purpose experimental tool available, which allows us to quickly and realistically simulate all kind of real-world problems and rehabilitation exercises for upper-limb impaired patients. Additionally, other scenarios such as prostheses simulations and control modes can be quickly implemented and tested.

ABSTRACT:3D surface models with high resolution and high accuracy are of great value in many applications, especially if these models are true to scale. As a promising alternative to active scanners (light section, structured light, laser scanners, etc.) new photogrammetric approaches are coming up. They use modern structure from motion (SfM) techniques, using the camera as main sensor. Unfortunately, the accuracy and resolution achievable with the available tools is very limited. When reconstructing large objects with high resolution an unacceptably high laborious effort is another problem. This paper shows an approach to overcome these limitations. It combines the strengths of modern surface reconstruction techniques from the remote sensing sector with novel SfM technologies, resulting in accurate 3D models of indoor and outdoor scenes. Starting with the image acquisition all particular steps to a final 3D model are explained. Finally the results of the evaluation of the approach at different indoor scenes are presented.

} , abstract = { In this paper we present a system for operation and testing of different UAVs. The system allows easy development and modification of control and mission software. The system is composed of hard-and software modules with a standardized interface. We have been using the system with rotary and fixed wing UAVs with a takeoff mass between 10 and 100 kg. For larger platforms the system can be used in a redundant setup. The software modules are integrated in a special real-time framework , which supports execution , scheduling , communication and system monitoring. A modular simulation and control in frastru cture allows for flexible , integrated design and analysis of control laws. The code for the computational part of the modules can be generated from Matlab / Simulink-models or from Modelica-models. The system supports debugging , soft-and hardware in the loop simulations , operator training as well as real flight experiments. The main design concepts are explained at hand of our solar powered high altitude platform ELHASPA and the 10 years experience in development and operation will be summarized .} , url = { http :// ieeexplore. ieee. org / xpl / art icleDet ails. jsp ? arnumber =6580042} }

We present an approach on training classifiers or regressors using the latent embedding of variational auto-encoders (VAE), an unsupervised deep learning method, as features. Usually VAEs are trained using unlabeled data and independently from the classifier, whereas we investigate and analyze the performance of a classifier or regressor that is trained jointly with the variational deep network. We found that models trained this way can improve the embedding s.t. to increase classification performance, and also can be used for semi-supervised learning, building up the information extracting latent representation in an incremental fashion. The model was tested on two widely known computer vision benchmarks, and its generalization power was evaluated on an independent dataset. Additionally, generally applicable statistical methods are presented for evaluating similarly performing classifiers, and used to quantify the performance increase. The general applicability and ease-of-use of deep learning approaches allows for a wide applicability of the method.