Dense Object Nets (DONs) by Florence, Manuelli and Tedrake (2018) introduced dense object descriptors as a novel visual object representation for the robotics community. It is suitable for many applications including object grasping, policy learning, etc. DONs map an RGB image depicting an object into a descriptor space image, which implicitly encodes key features of an object invariant to the relative camera pose. Impressively, the self-supervised training of DONs can be applied to arbitrary objects and can be evaluated and deployed within hours. However, the training approach relies on accurate depth images and faces challenges with small, reflective objects, typical for industrial settings, when using consumer grade depth cameras. In this paper we show that given a 3D model of an object, we can generate its descriptor space image, which allows for supervised training of DONs. We rely on Laplacian Eigenmaps (LE) to embed the 3D model of an object into an optimally generated space. While our approach uses more domain knowledge, it can be efficiently applied even for smaller and reflective objects, as it does not rely on depth information. We compare the training methods on generating 6D grasps for industrial objects and show that our novel supervised training approach improves the pick-and-place performance in industry-relevant tasks.

We introduce a mobile device for visual calibration of a large amount of high resolution digital images to support point cloud generation. This external nomadic device provides additional calibration information to be fed into standard 3D scene reconstruction software. Thus, gaps of non-overlapping camera images can be bridged for the calibration process. Point cloud processing significantly speeds up by reducing algorithmic complexity and manual interactions. We show a performance evaluation of an appropriate nomadic image calibration device demonstrator. Finally, we present the 3D reconstruction of a former in-ground mine for archaeological research as an application.

This work addresses the applicability of a switched queuing network as the sole communication network in an aircraft cabin, and proposes an algorithm based on a mixed-integer program to determine hard bounds for the end-to-end delay. These hard bounds guarantee mandatory performance bounds for safety-relevant functions in the aircraft cabin, such as audio announcements or smoke detection. Techniques from the field of deterministic Network Calculus are used to benchmark the results from our novel approach. The results show that our solution allows improved mapping of non-preemptive queuing networks, compared to relevant state-of-the-art approaches.

Recent studies observed video download platforms which contribute a large share to the overall traffic mix in today's operator networks. Traffic related to video downloads has reached a level where operators, network equipment vendors, and standardization organizations such as the IETF start to explore methods in order to reduce the traffic load in the network. Success or failure of these techniques depend on caching potentials of the target applications' traffic patterns. Our work aims at providing detailed insight into caching potentials of one of the leading video serving platforms: YouTube. We monitored interactions of users of a large operator network with the YouTube video distribution infrastructure for the time period of one month. From these traffic observations, we examine parameters that are relevant to the operation and effectiveness of an in-network cache deployed in an edge-network. Furthermore, we use our monitoring data as input for a simulation and determine the caching benefits that could have been observed if caching had been deployed.

The performance of a mesh network is mainly affected by the utilized routing protocol and its capability to detect topology changes and to select stable and reliable routes. In real-world scenarios, a high fraction of links have asymmetric characteristics which has to be concerned by routing protocols in order to find optimized routes. The latest version of the Better Approach to Mobile Adhoc Networking protocol (B.A.T.M.A.N.) introduces its own routing metric, addressing the problem of integrating asymmetric links efficiently in the network topology. In this work, we compare version III and IV of the B.A.T.M.A.N protocol in terms of delivery ratio, average end-to-end hop count and generated overhead in two scenarios with a high fraction of asymmetric links to assess the quality of the newly introduced mechanisms on the performance of the protocol.

Mesh routing protocols are specifically designed to meet the challenges resulting from frequent topology changes. In addition, they must generate and maintain reliable routes that are optimized with respect to QoS or energy efficiency. Routing protocols are usually developed for a set of scenarios with a certain traffic pattern and network architecture. Some protocols can be configured to achieve good performance in different kind of scenarios. However, the capability of the protocols to adapt themselves to different network characteristics often comes at the price of increased complexity. In this paper we introduce a statistic-based approach towards routing in mesh networks which is able to deal with many of the challenges arising in networks suffering from topology changes without the need of complex algorithms or a huge amount of memory.