Register now After registration you will be able to apply for this opportunity online.
This opportunity is not published. No applications will be accepted.
Sensor Fusion with Visual Motion Tracking for Airborne Wind Energy Systems
The goal of this master thesis is to develop and implement a sensor fusion scheme for AWE systems which combines measurements from the visual tracking system with onboard inertial measurements, GPS and possibly other sensors.
Keywords: Airborne Wind Energy, Power Kites, State Estimation, Sensor Fusion
Airborne Wind Energy (AWE) systems harvest wind energy by exploiting the aerodynamic forces generated by autonomous tethered kites, flying fast in crosswind conditions. This technology is able to reach higher altitudes than conventional wind turbines, where the wind is generally stronger and more consistent, while at the same time reducing the construction and installation costs of the generator.
This project builds on previous work in which a visual motion tracking system was developed. The system detects key features of AWE kites, such as position and flight direction, in real-time. The project hardware combines an industrial pan-tilt unit, a high framerate studio camera with a telescopic zoom lens and a processing unit. The detection and tracking software is based on a neural network algorithm.
Airborne Wind Energy (AWE) systems harvest wind energy by exploiting the aerodynamic forces generated by autonomous tethered kites, flying fast in crosswind conditions. This technology is able to reach higher altitudes than conventional wind turbines, where the wind is generally stronger and more consistent, while at the same time reducing the construction and installation costs of the generator.
This project builds on previous work in which a visual motion tracking system was developed. The system detects key features of AWE kites, such as position and flight direction, in real-time. The project hardware combines an industrial pan-tilt unit, a high framerate studio camera with a telescopic zoom lens and a processing unit. The detection and tracking software is based on a neural network algorithm.
The goal of this master thesis is to develop and implement a sensor fusion scheme which combines measurements from the visual tracking system with onboard inertial measurements, GPS and possibly other sensors. By incorporating advanced estimation techniques and appropriate models the accuracy and reliability of the state estimate of the kite system is to be improved. The project will offer the possibility to test the developed state estimation method on a real world kite system. The previous work described in the references below can form a basis from which to start the project.
**References:**
- Henrik Hesse, Max Polzin, Tony A. Wood, and Roy S. Smith. "Visual Motion Tracking and Sensor Fusion for Kite Power Systems." In Airborne Wind Energy, pp. 413-438. Springer, Singapore, 2018.
- Max Polzin, Tony A. Wood, Henrik Hesse, and Roy S. Smith. "State Estimation for Kite Power Systems with Delayed Sensor Measurements." IFAC-PapersOnLine 50, no. 1 (2017): 11959-11964.
- Shin Watanabe, „Real-Time Visual Kite Tracking System: Vision, Estimation and Control”, Master Thesis, ETH Zurich, 2018
**Requirements:**
- A solid background in state estimation methods.
- Experience with ROS/c++ are preferred.
The goal of this master thesis is to develop and implement a sensor fusion scheme which combines measurements from the visual tracking system with onboard inertial measurements, GPS and possibly other sensors. By incorporating advanced estimation techniques and appropriate models the accuracy and reliability of the state estimate of the kite system is to be improved. The project will offer the possibility to test the developed state estimation method on a real world kite system. The previous work described in the references below can form a basis from which to start the project.
**References:**
- Henrik Hesse, Max Polzin, Tony A. Wood, and Roy S. Smith. "Visual Motion Tracking and Sensor Fusion for Kite Power Systems." In Airborne Wind Energy, pp. 413-438. Springer, Singapore, 2018. - Max Polzin, Tony A. Wood, Henrik Hesse, and Roy S. Smith. "State Estimation for Kite Power Systems with Delayed Sensor Measurements." IFAC-PapersOnLine 50, no. 1 (2017): 11959-11964. - Shin Watanabe, „Real-Time Visual Kite Tracking System: Vision, Estimation and Control”, Master Thesis, ETH Zurich, 2018
**Requirements:**
- A solid background in state estimation methods. - Experience with ROS/c++ are preferred.
- Eva Ahbe (ahbee@control.ee.ethz.ch)
- Dr. Tony Wood (wood.t@unimelb.edu.au)
- Dr. Nikolaos Kariotoglou (nk@seervision.ch)
- Eva Ahbe (ahbee@control.ee.ethz.ch) - Dr. Tony Wood (wood.t@unimelb.edu.au) - Dr. Nikolaos Kariotoglou (nk@seervision.ch)