This practical course is aligned with Mobile Robotics, following its theoretical contents with the aim of applying them practically on a drone flying in simulation and ultimately the real world (indoors).

There will be no pre-meeting; this practical module will be explained in the first Lecture of Mobile Robotics. Please simply indicate your preference in the "matching system" – there is no separate application process.

• Manual steering of an MAV in simulation (ROS/Gazebo) and the real world (via WiFi and ROS)
• Implementation of a Visual-Inertial Localisation system assuming a known environment (simulation and real)
• Adopting dense volumetric mapping (moved RGB-D-inertial camera in simulation and in real-world)
• Training and deploying Deep-Learning-based object/obstacle recognition and pose estimation
• Implementation of a feedback-control architecture for autonomous MAV flight (simulation and real)
• Integration of MAV motion planning and navigation algorithms (simulation and real)
• Completion of a Challenge: MAV flight through cluttered environment including automatic take-off and landing, and an open element to demo an element from Spatial AI, navigation, control, etc.

Passion for mobile robots and drones, as well as solid mathematical foundations regarding analysis, linear algebra, and probability theory. The exercises and practicals will require solid knowledge of Python and C++ programming. Participation in “Advanced Mobile Robotics” is a requirement, since the elements of that course are implemented in practice here. Furthermore, participation in the following courses is highly recommended:

• Mobile Robotics
• Computer Vision II: Multi-View Geometry (IN2228),
• Robotics (IN2067),
• Robot Motion Planning (IN2138),
• Introduction to Deep Learning (IN2346)
• Motion planning for autonomous vehicles (IN2106, IN0012, IN4221)