Research Projects

Our research on intelligent autonomous systems in unstructured outdoor environments focuses on the following topics:

• Simultaneous Localization and Mapping (SLAM)
• especially Visual SLAM (monocular and steroscopic approaches)
• biologically inspired approaches to navigation, filtering and environmental perception
• stereo vision
• further aspects of visual perception
• navigation and path control of autonomous systems on the ground and in the air
• flight control of complex aerial systems

Further research areas are process control and process optimization using knowledge based methods, as well as modelling, simulation, and control of complex processes in industrial domains.

Information in english are only available for the following research topics. Plese see our german pages for more information.

Current state of the art solutions of the SLAM problem are based on efficient sparse optimization techniques and represent the problem as probabilistic constraint graphs. For example in pose graphs the nodes represent poses and the edges between them express spatial information (e.g. obtained from odometry) and information on loop closures. The task of constructing the graph is delegated to a front-end that has access to the available sensor information.

The optimizer, the so called back-end of the system, relies heavily on the topological correctness of the graph structure and is not robust against misplaced constraint edges. Especially edges representing false positive loop closures will lead to the divergence of current solvers.

We work on a novel problem formulation that allows the back-end to change parts of the topological structure of the graph during the optimization process. The back-end can thereby discard loop closures and converge towards correct solutions even in the presence of false positive loop closures. This largely increases the overall robustness of the SLAM system and closes a gap between the sensor-driven front-end and the back-end optimizers.

The ability to recognize known places is an essential competence of any intelligent system that operates autonomously over longer periods of time. Approaches that rely on the visual appearance of distinct scenes have recently been developed and applied to large scale SLAM scenarios. FAB-Map is maybe the most successful of these systems.

We propose BRIEF-Gist, a very simplistic appearance-based place recognition system based on the BRIEF descriptor. BRIEF-Gist is much more easy to implement and more efficient compared to recent approaches like FAB-Map.

Despite its simplicity, we can show that it performs comparably well as a front-end for large scale SLAM. We benchmark our approach using two standard datasets and perform SLAM on the 66 km long urban St. Lucia dataset.

Since the 1970's different types of neurons involved in spacial navigation have been identified in the brains of rats, primates and humans. Several experiments of different researchers show that these cells code the position and orientation of the animal in its environment.

Neurologists and theoretical biologists have been developing models that help to understand the behaviour of animals as well as humans in different situations. These models explain the workings of the different cell assemblies and their connections with other areas in the brain.

We are interested in these developements and want to derive efficient algorithms that help solving navigation tasks and SLAM on autonomous mobile robots. Our goal is explicitly not to mimic the behaviour of the involved biological processes on the level of single neurons or even spike trains. Instead, we want to understand the principles behind these biological processes and project them onto higher levels of abstraction that are suitable for implementation and application on autonomous systems.

Our research interests focus on enabling autonomous micro aerial vehicles (MAVs) to be applicable in a variety of civil applications, mainly in the areas of emergency response, disaster control, and environmental monitoring. These scenarios require a high level of autonomy, reliability and general robustness. In the SkeyeCopter-project we concentrate on intelligent algorithms for environmental perception, sensor fusion and control strategies. Three Hummingbird micro UAVs are used for validation and experiments.

For our micro-UAV project SkeyeCopter we felt the need to develop an interface to a simulation environment that would allow faster development and evaluation of algorithms on the behavioural level of a single UAV or swarms of them. We chose to use and build upon USARSim, a simulation framework widely used in the RoboCup community.

We developed interfaces between USARSim and the already existing software modules responsible for UAV control. This interface is completely transparent to higher software layers, allowing the same code to be run in the simulation as well as on the real hardware without any change.

Recently, we contributed some of our work to the USARSim community. Check out e.g. our image server or the corrected sonar sensor.

ProAut
07 October 2011

• 
• 
• 
• 
• 

Technische Universität Chemnitz, 09107 Chemnitz

• Imprint
• - Copyright © 2012 by Chemnitz UT. All rights reserved.