Dr.-Ing. Sven Lange

A Credible and Robust Approach to Ego-Motion Estimation Using an Automotive Radar

Abstract: Consistent motion estimation is fundamental for all mobile autonomous systems. While this sounds like an easy task, often, it is not the case because of changing environmental conditions affecting odometry obtained from vision, Lidar, or the wheels themselves. Unsusceptible to challenging lighting and weather conditions, radar sensors are an obvious alternative. Usually, automotive radars return a sparse point cloud, representing the surroundings. Utilizing this information to motion estimation is challenging due to unstable and phantom measurements, which result in a high rate of outliers. We introduce a credible and robust probabilistic approach to estimate the ego-motion based on these challenging radar measurements; intended to be used within a loosely-coupled sensor fusion framework. Compared to existing solutions, evaluated on the popular nuScenes dataset and others, we show that our proposed algorithm is more credible while not depending on explicit correspondence calculation.

Haggag, K., Lange, S., Pfeifer, T. & Protzel, P. (2022) A Credible and Robust Approach to Ego-Motion Estimation Using an Automotive Radar. IEEE Robotics and Automation Letters (RA-L). DOI: 10.1109/LRA.2022.3162644

Advancing Mixture Models for Least Squares Optimization

Abstract: Gaussian mixtures are a powerful and widely used tool to model non-Gaussian estimation problems. They are able to describe measurement errors that follow arbitrary distributions and can represent ambiguity in assignment tasks like point set registration or tracking. However, using them with common least squares solvers is still difficult. Existing approaches are either approximations of the true mixture or prone to convergence issues due to their strong nonlinearity. We propose a novel least squares representation of a Gaussian mixture, which is an exact and almost linear model of the corresponding log-likelihood. Our approach provides an efficient, accurate and flexible model for many probabilistic estimation problems and can be used as cost function for least squares solvers. We demonstrate its superior performance in various Monte Carlo experiments, including different kinds of point set registration. Our implementation is available as open source code for the state-of-the-art solvers Ceres and GTSAM.

Pfeifer, T., Lange, S. & Protzel, P. (2021) Advancing Mixture Models for Least Squares Optimization. IEEE Robotics and Automation Letters (RA-L). DOI: 10.1109/LRA.2021.3067307

Schlussbericht zum Vorhaben smartLoc - Robuste Satellitennavigation mit generalisierten Faktorgraphen

Abstract: Der vorliegende Schlussbericht beschreibt die Ergebnisse von smartLoc. Ein Projekt, welches sich mit Methodik beschäftigte, Positionsschätzungen auf Basis von GNSS-Rohdaten zu berechnen \textendash unter idealen Bedingungen ist dies ein gelöstes Problem, nicht jedoch in urbanen Gebieten mit hohem Non-Line-of-Sight (NLOS) Anteil der empfangenen Satellitenmessungen in Verbindung mit Massenmarkt-GNSS Empfängern. In diesem Projekt sollte daher ein algorithmisches Verfahren entwickelt und untersucht werden, das eine wesentliche Verbesserung der Integrität und auch der Genauigkeit der Positionsschätzung in Umgebungen mit beeinträchtigtem Satellitenempfang ermöglicht. Das vorliegende Dokument motiviert die Problemstellung im Zusammenhang mit dem aktuellen Stand der Wissenschaft und beschreibt im Anschluss die Ergebnisse sowie den Projektablauf. Die Ergebnisse beschreiben und analysieren die innerhalb des Projektes durchgeführte Messdatenakquise zur Aufnahme geeigneter GNSS-Datensätze. Sie sind neben simulierten Daten sowie experimenten mit UWB-Funkortung die basis zur Evaluierung unseres robusten Faktorgraph-basierten Optimierungsansatzes. Aufbauend auf dem Stand-der-Technik modellieren wir multimodale Verteilungen zur Beschreibung des Fehlerverhaltens von GNSS-Pseudorange-Messungen, um diese in einen optimierungsbasierten Ansatz zur Positionsschätzung berücksichtigen zu können. Durch diese spezielle Modellierung können fehlerhafte (NLOS) Messungen ohne spezielle Vorverarbeitung direkt im Optimierungsproblem integriert werden, ohne durch diese Ausrei\sser fehler in der Positionsschätzung zu erzeugen. Daneben ergibt sich noch ein weiterer Vorteil: durch die wirklichkeitsnähere Modellierung der Fehlerverteilung wird auch die berechnete Zuverlässigkeit (Kovarianz) der Positionsschätzung realistischer. Standard Verfahren führen in einem solchen Fall typischerweise zu zuversichtlichen (over-confident) Aussagen.

Lange, S., Pfeifer, T., Weissig, P., Reisdorf, P. & Protzel, P. (2018) Schlussbericht zum Vorhaben smartLoc - Robuste Satellitennavigation mit generalisierten Faktorgraphen, TU Chemnitz, Professur Prozessautomatisierung. DOI: 10.2314/GBV:1027946380

Dynamic Covariance Estimation -- A Parameter Free Approach to Robust Sensor Fusion

Abstract: In robotics, non-linear least squares estimation is a common technique for simultaneous localization and mapping. One of the remaining challenges are measurement outliers leading to inconsistency or even divergence within the optimization process. Recently, several approaches for robust state estimation dealing with outliers inside the optimization back-end were presented, but all of them include at least one arbitrary tuning parameter that has to be set manually for each new application. Under changing environmental conditions, this can lead to poor convergence properties and erroneous estimates. To overcome this insufficiency, we propose a novel robust algorithm based on a parameter free probabilistic foundation called Dynamic Covariance Estimation. We derive our algorithm directly from the probabilistic formulation of a Gaussian maximum likelihood estimator. Through including its covariance in the optimization problem, we empower the optimizer to approximate these to the sensor's real properties. Finally, we prove the robustness of our approach on a real world wireless localization application where two similar state-of-the-art algorithms fail without extensive parameter tuning.

Pfeifer, T., Lange, S. & Protzel, P. (2017) Dynamic Covariance Estimation -- A Parameter Free Approach to Robust Sensor Fusion. In Proc. of Intl. Conf. on Multisensor Fusion and Integration for Intelligent Systems (MFI). DOI: 10.1109/MFI.2017.8170347

TUC-Bot: A Microcontroller based Robot for Education

Abstract: We describe the concept of a mobile robotics course for undergraduate students from an educational point of view in terms of learning goals, experiences, and hardware design. The course as well as the hardware was continuously improved over more than a decade. Hence, we like to describe our motivation and the current structure of the course in order to share our experiences as an inspiration for similar courses.

Lange, S., Weissig, P., Uhlig, A. & Protzel, P. (2017) TUC-Bot: A Microcontroller based Robot for Education. In Proc. of Intl. Conf. on Robotics in Education (RiE). DOI: 10.1007/978-3-319-62875-2_18

The Problem of Comparable GNSS Results — An Approach for a Uniform Dataset with Low-Cost and Reference Data

Abstract: Localization and navigation are two key factors for our globalized world. Driven by cost-effective end-user devices, position estimation using Global Navigation Satellite Systems (GNSS) is common sense. Using the pseudorange measurements as input, many research groups developed their own approaches for estimating position information and evaluated it in simulation or real-world scenarios. Surprisingly, a common publicly available dataset for comparing such algorithms against each other has not been established. We pursue the idea of a uniform, free to use dataset collected by a low-cost receiver in conjunction with associated reference data originating from a high-precision device. [...] Our datasets are associated with the smartLoc project and are available online at: www.mytuc.org/GNSS

Reisdorf, P., Pfeifer, T., Breßler, J., Bauer, S., Weissig, P., Lange, S., Wanielik, G. & Protzel, P. (2016) The Problem of Comparable GNSS Results — An Approach for a Uniform Dataset with Low-Cost and Reference Data. In Proc. of Intl. Conf. on Advances in Vehicular Systems (VEHICULAR). ISBN: 978-1-61208-515-9

Robust Factor Graph Optimization — A Comparison for Sensor Fusion Applications

Abstract: While many applications of sensor fusion suffer from the occurrence of outliers, a broad range of outlier robust graph optimization techniques has been developed for simultaneous localization and mapping. In this paper we investigate the performance of some of the most advanced algorithms for a simulated wireless localization setting affected by non-Gaussian errors. With this first analysis we can show some of the advantages and disadvantages that are connected with the different concepts behind Max-Mixture, Generalized iSAM, Switchable Constraints and Dynamic Covariance Scaling.

Pfeifer, T., Weissig, P., Lange, S. & Protzel, P. (2016) Robust Factor Graph Optimization — A Comparison for Sensor Fusion Applications. In Proc. of Intl. Conf. on Emerging Technologies and Factory Automation (ETFA). DOI: 10.1109/ETFA.2016.7733598

Two Autonomous Robots for the DLR SpaceBot Cup — Lessons Learned from 60 Minutes on the Moon

Abstract: The SpaceBot Cup 2015 was a national robotics contest among 10 German universities and research institutes. It was organized by the German Aerospace Agency DLR and required 60 minutes of autonomous operation in a challenging environment. The robots had to explore and map the environment, find, transport and manipulate two objects, and navigate back to the landing site without global position information like GPS under very restricted communication. This paper describes our concept, the used systems and algorithms, and our experiences in terms of lessons learned.

Lange, S., Wunschel, D., Schubert, S., Pfeifer, T., Weissig, P., Uhlig, A., Truschzinski, M. & Protzel, P. (2016) Two Autonomous Robots for the DLR SpaceBot Cup — Lessons Learned from 60 Minutes on the Moon. In Proc. of Intl. Symposium on Robotics (ISR)

Map Enhancement with Track-Loss Data in Visual SLAM

Abstract: Mobile robots often do not know their environment in advance and have to explore their surroundings after mission start. So, a robot has to localize itself and build a map in parallel, which represents the well-known SLAM problem. In case of a three-dimensional environment, a visual SLAM system is a reasonable choice and different SLAM systems exist. A promising approach of existing algorithms is ORB-SLAM which provides a computationally efficient (CPU-only), robust and open-source SLAM system. However, we noticed a drawback which causes a loss of map information after a track loss – e.g. in case of a fast rotational movement, ORB-SLAM fails to localize itself and starts a relocalization loop as long as it cannot recognize a previously visited place. Meanwhile, the incoming images are solely used for relocalization in the map and not used for enhancing the map. We coin these images track-loss data and hypothesize that this data can be beneficially used to enhance the map after a successful relocalization. In this paper, we discuss ways to exploit the track-loss data for map enhancement in ORB-SLAM, and show the result of an extension in comparison to the original algorithm with a proof-of-concept outdoor experiment.

Schubert, S., Lange, S., Neubert, P. & Protzel, P. (2016) Map Enhancement with Track-Loss Data in Visual SLAM. In Proc. of Intl. Conf. on Intelligent Robots and Systems (IROS) Workshop on State Estimation and Terrain Perception for All Terrain Mobile Robots

Phobos and Deimos on Mars — Two Autonomous Robots for the DLR SpaceBot Cup

Abstract: In 2013, ten teams from German universities and research institutes participated in a national robot competition called SpaceBot Cup organized by the DLR Space Administration. The robots had one hour to autonomously explore and map a challenging Mars-like environment, find, transport, and manipulate two objects, and navigate back to the landing site. Localization without GPS in an unstructured environment was a major issue as was mobile manipulation and very restricted communication. This paper describes our system of two rovers operating on the ground plus a quadrotor UAV simulating an observing orbiting satellite. [...] Despite (or because of) faults, communication loss and breakdowns, it was a valuable experience with many lessons learned.

Sünderhauf, N., Neubert, P., Truschzinski, M., Wunschel, D., Pöschmann, J., Lange, S. & Protzel, P. (2014) Phobos and Deimos on Mars — Two Autonomous Robots for the DLR SpaceBot Cup. In Proc. of Intl. Symposium on Artificial Intelligence, Robotics and Automation in Space (iSAIRAS)

Faktorgraph-basierte Sensordatenfusion zur Anwendung auf einem Quadrocopter

Abstract: Die Sensordatenfusion ist eine allgegenwärtige Aufgabe im Bereich der mobilen Robotik und darüber hinaus. In der vorliegenden Arbeit wird das typischerweise verwendete Verfahren zur Sensordatenfusion in der Robotik in Frage gestellt und anhand von neuartigen Algorithmen, basierend auf einem Faktorgraphen, gelöst sowie mit einer korrespondierenden Extended-Kalman-Filter-Implementierung verglichen. Im Mittelpunkt steht dabei das technische sowie algorithmische Sensorkonzept für die Navigation eines Flugroboters im Innenbereich. Ausführliche Experimente zeigen die Qualitätssteigerung unter Verwendung der neuen Variante der Sensordatenfusion, aber auch Einschränkungen und Beispiele mit nahezu identischen Ergebnissen beider Varianten der Sensordatenfusion. Neben Experimenten anhand einer hardwarenahen Simulation wird die Funktionsweise auch anhand von realen Hardwaredaten evaluiert.

Lange, S. (2013) Faktorgraph-basierte Sensordatenfusion zur Anwendung auf einem Quadrocopter. Dissertation: TU Chemnitz

Switchable Constraints and Incremental Smoothing for Online Mitigation of Non-Line-of-Sight and Multipath Effects

Abstract: Reliable vehicle positioning is a crucial requirement for many applications of advanced driver assistance systems. While satellite navigation provides a reasonable performance in general, it often suffers from multipath and non-line-of-sight errors when it is applied in urban areas and therefore does not guarantee consistent results anymore.
Our paper proposes a novel online method that identifies and excludes the affected pseudorange measurements. Our approach does not depend on additional sensors, maps, or environmental models. We rather formulate the positioning problem as a Bayesian inference problem in a factor graph and combine the recently developed concept of switchable constraints with an algorithm for efficient incremental inference in such graphs. We furthermore introduce the concepts of auxiliary updates and factor graph pruning in order to accelerate convergence while keeping the graph size and required runtime bounded. A real-world experiment demonstrates that the resulting algorithm is able to successfully localize despite a large number of satellite observations are influenced by NLOS or multipath effects.

Sünderhauf, N., Obst, M., Lange, S., Wanielik, G. & Protzel, P. (2013) Switchable Constraints and Incremental Smoothing for Online Mitigation of Non-Line-of-Sight and Multipath Effects. In Proc. of IEEE Intelligent Vehicles Symposium (IV). DOI: 10.1109/IVS.2013.6629480