Julian Förster

Joël Bachmann, Kenneth Blomqvist, Julian Förster et al.

Unsupervised representation learning techniques, such as learning word embeddings, have had a significant impact on the field of natural language processing. Similar representation learning techniques have not yet become commonplace in the context of 3D vision. This, despite the fact that the physical 3D spaces have a similar semantic structure to bodies of text: words are surrounded by words that are semantically related, just like objects are surrounded by other objects that are similar in concept and usage. In this work, we exploit this structure in learning semantically meaningful low dimensional vector representations of objects. We learn these vector representations by mining a dataset of scanned 3D spaces using an unsupervised algorithm. We represent objects as point clouds, a flexible and general representation for 3D data, which we encode into a vector representation. We show that using our method to include context increases the ability of a clustering algorithm to distinguish different semantic classes from each other. Furthermore, we show that our algorithm produces continuous and meaningful object embeddings through interpolation experiments.

Julian Förster, Lionel Ott, Juan Nieto et al.

Symbolic planning can provide an intuitive interface for non-expert users to operate autonomous robots by abstracting away much of the low-level programming. However, symbolic planners assume that the initially provided abstract domain and problem descriptions are closed and complete. This means that they are fundamentally unable to adapt to changes in the environment or task that are not captured by the initial description. We propose a method that allows an agent to automatically extend its skill set, and thus the abstract description, upon encountering such a situation. We introduce strategies for generalizing from previous experience, completing sequences of key actions and discovering preconditions to ensure the efficiency of our skill sequence exploration scheme. The resulting system is evaluated in simulation on object rearrangement tasks. Compared to a Monte Carlo Tree Search baseline, our strategies for efficient search have on average a 29% higher success rate at a 68% faster runtime.

Kenneth Blomqvist, Michel Breyer, Andrei Cramariuc et al.

With humankind facing new and increasingly large-scale challenges in the medical and domestic spheres, automation of the service sector carries a tremendous potential for improved efficiency, quality, and safety of operations. Mobile robotics can offer solutions with a high degree of mobility and dexterity, however these complex systems require a multitude of heterogeneous components to be carefully integrated into one consistent framework. This work presents a mobile manipulation system that combines perception, localization, navigation, motion planning and grasping skills into one common workflow for fetch and carry applications in unstructured indoor environments. The tight integration across the various modules is experimentally demonstrated on the task of finding a commonly available object in an office environment, grasping it, and delivering it to a desired drop-off location. The accompanying video is available at https://youtu.be/e89_Xg1sLnY.

Philipp Oettershagen, Julian Förster, Lukas Wirth et al.

Solar-powered aircraft promise significantly increased flight endurance over conventional aircraft. While this makes them promising candidates for large-scale aerial inspection missions, their structural fragility necessitates that adverse weather is avoided using appropriate path planning methods. This paper therefore presents MetPASS, the Meteorology-aware Path Planning and Analysis Software for Solar-powered UAVs. MetPASS is the first path planning framework in the literature that considers all aspects that influence the safety or performance of solar-powered flight: It avoids environmental risks (thunderstorms, rain, wind, wind gusts and humidity) and exploits advantageous regions (high sun radiation or tailwind). It also avoids system risks such as low battery state of charge and returns safe paths through cluttered terrain. MetPASS imports weather data from global meteorological models, propagates the aircraft state through an energetic system model, and then combines both into a cost function. A combination of dynamic programming techniques and an A*-search-algorithm with a custom heuristic is leveraged to plan globally optimal paths in station-keeping, point-to-point or multi-goal aerial inspection missions with coverage guarantees. A full software implementation including a GUI is provided. The planning methods are verified using three missions of ETH Zurich's AtlantikSolar UAV: An 81-hour continuous solar-powered station-keeping flight, a 4000km Atlantic crossing from Newfoundland to Portugal, and two multi-glacier aerial inspection missions above the Arctic Ocean performed near Greenland in summer 2017.