Roland Siegwart

Biography

Originaire d'Altdorf (UR) et d'Oberkirch (LU), Roland Siegwart est né en 1959 à Lausanne. Après une enfance à Schwyz, il a étudié à l'EPFZ et a obtenu son diplôme en génie mécanique en 1983. Il a travaillé ensuite comme assistant de recherche à l'EPFZ. En 1989, il a obtenu son doctorat, sa thèse traitant de l'application des paliers magnétiques sur les machines d'usinage de grande vitesse.

De 1989 à 1990, il a effectué des recherches à l'Université de Stanford en Californie (USA) et a participé à des projets en microrobotique. De retour en Suisse, il a rejoint l'Institut de robotique à l'EPFZ. Comme directeur remplaçant de l'Institut de Robotique, il a organisé les activités dans la micro- et nanorobotique. Il a mis notamment au pointuncourensystèmesélectroméca-niques appliqués.

Depuis 1990, R. Siegwart a été engagé en parallèle comme vice président de MECOS Traxler AG, une entreprise spin-off' de l'EPFZ. Il a dirigé de nombreux projets industriels dans le domaine des paliers magnétiques. ProfesseurauDépartementdemicrote-chnique de l'EPFL depuis 1996, R. Siegwart est responsable de la recherche en systèmes microtechniques autonomes. Le champ principal de ses activités porte sur les robots et les microrobots mobiles ainsi que les microsystèmes dynamiques et de très hautes performances.

Official source

https://people.epfl.ch/roland.siegwart

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Related units (8)

Related units

Courses taught by this person

Related research domains (88)

Related research domains

Related publications (281)

Related publications

People doing similar research (95)

People doing similar research

C-blox: A Scalable and Consistent TSDF-based Dense Mapping Approach

Roland Siegwart

In many applications, maintaining a consistent dense map of the environment is key to enabling robotic platforms to perform higher level decision making. Several works have addressed the challenge of creating precise dense 3D maps from visual sensors providing depth information. However, during operation over longer missions, reconstructions can easily become inconsistent due to accumulated camera tracking error and delayed loop closure. Without explicitly addressing the problem of map consistency, recovery from such distortions tends to be difficult. We present a novel system for dense 3D mapping which addresses the challenge of building consistent maps while dealing with scalability. Central to our approach is the representation of the environment as a collection of overlapping Truncated Signed Distance Field (TSDF) subvolumes. These subvolumes are localized through feature-based camera tracking and bundle adjustment. Our main contribution is a pipeline for identifying stable regions in the map, and to fuse the contributing subvolumes. This approach allows us to reduce map growth while still maintaining consistency. We demonstrate the proposed system on a publicly available dataset and simulation engine, and demonstrate the efficacy of the proposed approach for building consistent and scalable maps. Finally we demonstrate our approach running in real-time onboard a lightweight Micro Aerial Vehicle (MAV).

2019

Sensor fusion is a fundamental process in robotic systems as it extends the perceptual range and increases robustness in real-world operations. Current multi-sensor deep learning based semantic segmentation approaches do not provide robustness to under-performing classes in one modality, or require a specific architecture with access to the full aligned multi-sensor training data. In this work, we analyze statistical fusion approaches for semantic segmentation that overcome these drawbacks while keeping a competitive performance. The studied approaches are modular by construction, allowing to have different training sets per modality and only a much smaller subset is needed to calibrate the statistical models. We evaluate a range of statistical fusion approaches and report their performance against state-of-the-art baselines on both realworld and simulated data. In our experiments, the approach improves performance in IoU over the best single modality segmentation results by up to 5%. We make all implementations and configurations publicly available.

2019

Multiple Hypothesis Semantic Mapping for Robust Data Association

Roland Siegwart

In this letter, we present a semantic mapping approach with multiple hypothesis tracking for data association. As semantic information has the potential to overcome ambiguity in measurements and place recognition, it forms an eminent modality for autonomous systems. This is particularly evident in urban scenarios with several similar-looking surroundings. Nevertheless, it requires the handling of a non-Gaussian and discrete random variable coming from object detectors. Previous methods facilitate semantic information for global localization and data association to reduce the instance ambiguity between the landmarks. However, many of these approaches do not deal with the creation of completely globally consistent representations of the environment and typically do not scale well. We utilize multiple hypothesis trees to derive a probabilistic data association for semantic measurements by means of position, instance, and class to create a semantic representation. We propose an optimized mapping method and make use of a pose graph to derive a novel semantic SLAM solution. Furthermore, we show that semantic covisibility graphs allow for a precise place recognition in urban environments. We verify our approach using real-world outdoor dataset and demonstrate an average drift reduction of 33% w.r.t. the raw odometry source. Moreover, our approach produces 55% less hypotheses on average than a regular multiple hypothesis approach.

2019