Dr. Stefan LeuteneggerLecturer

Sensing capabilities in autonomous robotics



Bio

Stefan has worked on indoor service robots, drones and has a special interest in autonomous vehicles. The Smart Robotics Lab is led by Dr Stefan Leutenegger, Lecturer in Robotics (USA equivalent Assistant 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.

 

Research

Stefan’s research focuses on autonomous robot navigation, in particular on the sensing capabilities and the algorithms required to navigate in a potential unknown environment. Robotics research is experiencing an explosion, particularly triggered by four elements:

(1)   Technological innovation on cameras and imaging that can now allow 3D visualization and accurate distance assessment to objects;

(2)   Emergence of high-sensitivity and high-resolution sensors;

(3)   Increase in computational power that has enabled complex imaging analysis.

(4)   Development of algorithms that combine machine learning to facilitate semantic understanding (and not just the geometric understanding of an environment)

 

This is accelerating the development of more “intelligent” robots that increasingly adapt to human needs. 

 

Future applications

The field of robotics and, in particular, the merge with machine learning is promising the development of robots that are able to solve real problems. In particular, there are two fields that are likely to see an acceleration:

  • Robotics used for virtual reality, such as telepresence robots or drones.
  • Autonomous cars, where a lot of work is still needed to overcome existing safety barriers.

Other areas of expansion may include:

  • Microbots to allow emergency responders to explore areas that are difficult or dangerous to access.
  • Exoskeletons that might be used to augment the physical strength of humans.
  • Intelligent robots with human-like expressions and reactions.
  • Robotic networks that allow robots access databases, share information and learn from one another’s experience.