The goal of this project is to experiment and improve our recent multi-robot pose estimation algorithm.
The student will be able to develop innovative ways for robots collaboratively perform tasks such as manipulation and inspection.
Small, multi-rotor Unmanned Aerial Vehicles (UAVs) have become some of the most widely used robotic platforms due to their low cost and remarkable mobility. Nonetheless, their payload is very limited and so is the processing power and the sensing equipment that can be carried on-board. With these restrictions in mind, monocular cameras are some of the most appealing sensors for such vehicles. However several scenarios lack enough visual cues to enable position estimation without any augmentation of the scene.
This project aims to experiment and develop new ways to perform collaborative tasks using multiple ground and aerial vehicles with our recently published visual-inertial relative pose estimation. Please watch our youtube video - https://youtu.be/0auaPt5etHg
Refs
VI-RPE: Visual-Inertial Relative Pose Estimation for Aerial Vehicles " by Lucas Teixeira, Fabiola Maffra, Marco Moos and Margarita Chli - RA-L 2018
Small, multi-rotor Unmanned Aerial Vehicles (UAVs) have become some of the most widely used robotic platforms due to their low cost and remarkable mobility. Nonetheless, their payload is very limited and so is the processing power and the sensing equipment that can be carried on-board. With these restrictions in mind, monocular cameras are some of the most appealing sensors for such vehicles. However several scenarios lack enough visual cues to enable position estimation without any augmentation of the scene.
This project aims to experiment and develop new ways to perform collaborative tasks using multiple ground and aerial vehicles with our recently published visual-inertial relative pose estimation. Please watch our youtube video - https://youtu.be/0auaPt5etHg
Refs
VI-RPE: Visual-Inertial Relative Pose Estimation for Aerial Vehicles " by Lucas Teixeira, Fabiola Maffra, Marco Moos and Margarita Chli - RA-L 2018
- WP1: Research into state-of-the-art segmentation collaborative robotics.
- WP2: Familiarisation with our existing implementation of the relative pose estimation.
- WP3: Develop a set of collaborative task planners using relative pose estimation and computer vision in general.
- WP4: Experimentation and evaluation of these algorithms against state-of-the-art approaches.
- WP5: Further optimization of the pipeline of WP3 to work in challenging scenarios.
- WP6: Final evaluation of the methods and report writing.
- WP1: Research into state-of-the-art segmentation collaborative robotics. - WP2: Familiarisation with our existing implementation of the relative pose estimation. - WP3: Develop a set of collaborative task planners using relative pose estimation and computer vision in general. - WP4: Experimentation and evaluation of these algorithms against state-of-the-art approaches. - WP5: Further optimization of the pipeline of WP3 to work in challenging scenarios. - WP6: Final evaluation of the methods and report writing.
The student taking this project needs to be highly motivated. The following skills are desirable:
- Strong interest in active perception and vision-based navigation.
- Strong analytical skills.
- Background in C++.
The student taking this project needs to be highly motivated. The following skills are desirable:
- Strong interest in active perception and vision-based navigation. - Strong analytical skills. - Background in C++.
Your application must contain your most recent transcripts from bachelor and master studies. Lucas Teixeira - lteixeira@mavt.ethz.ch
Your application must contain your most recent transcripts from bachelor and master studies. Lucas Teixeira - lteixeira@mavt.ethz.ch