The Smart Robotics Lab focuses on enabling technologies for mobile robotics. Specifically, robots need dedicated sensing capabilities as well as algorithms for localisation inside a potentially unknown environment. This includes localisation and mapping with a suite of sensors, most importantly cameras, to be processed efficiently on-board to yield accurate results in real-time. As example platforms, we use Unmanned Aerial Systems (UAS) that run our software, allowing them to navigate through potentially unknown environments, completely autonomously, and without the need for external position tracking such as GPS.
Current Main Research Interests
As detailed in the Projects tab, the main areas of interest are the following:
- Building scalable and high-quality maps for robot navigation using computer vision.
- Multi-sensor fusion for more robust and accurate state estimation and mapping, e.g. making use of Inertial Measurement Units (IMUs) or knowledge about robot kinematics/dynamics.
- Leveraging Machine Learning (Deep Learning) to understand map semantics and other additional information about environment and robot motion.
- Novel camera systems, e.g. event cameras and how they could be used in robotic estimation.
- Interaction with the environment by linking robot estimation with control: from autonomous exploration to using manipulators in order to support active mapping and recognition.
- Application to real autonomous mobile robotic systems: ranging from ground robots, to flying small Unmanned Aerial Systems (UAS).
The Smart Robotics Lab is led by Dr Stefan Leutenegger, Senior Lecturer in Robotics (USA equivalent Associate Professor). Stefan furthermore co-leads the Dyson Robotics Lab together with Andrew Davison, working on very much related research. Stefan received a BSc and MSc in Mechanical Engineering from ETH Zurich in 2006, 2008, respectively, and a PhD in 2014, working at the Autonomous Systems Lab of ETH Zurich on Unmanned Solar Airplanes: Design and Algorithms for Efficient and Robust Autonomous Operation.