TUM Flyers

The aim of this project is to develop novel vision-based localization, 3D reconstruction, and navigation technologies for increasing the level of autonomy of MAV inspection systems and the systematic quality of inspections. The inspection of a structure such as a bridge with micro aerial vehicles (MAVs) is a highly challenging use-case for which we will develop a feasibility demonstration in this project. Inspection nowadays often is a costly and time-consuming process. Inspection teams need to climb through the structures, or special heavy equipment such as access lifts need to be employed. Current approaches using MAVs rely on GPS for autonomous navigation and require highly skilled and well trained pilots to maneuver the MAV close to structures. The vision-based technologies pursued in this project target at further automating and simplifying the use of MAVs in GPS-restricted or GPS-denied environments.

Systematic inspection and maintenance of the huge amount of structures in the EU such as industrial plants, wind power plants, or traffic infrastructure, e.g. bridges, is highly important for sustaining the productivity of Europe’s industry. Structures without timely maintenance treatments will likely require more costly treatments sooner than those properly maintained. Furthermore, sudden out-times of such structures due to deferred maintenance can lead to severe negative economic impact. In addition to their immense economic value, existing structures worldwide also may have major cultural value that must be preserved.

Nowadays, inspections of such structures are often done visually. Experienced inspection teams climb through the structures with the help of climbing equipment and access vehicles (manlift, bucket truck, etc.). This procedure is highly dangerous for the inspection teams, and is very time consuming and costly. It is also difficult for the team to perform a full and systematic inspection which may cause deficiencies to be overlooked. Finally, the inspection team typically has no accurate position information to exactly reference deficiencies, such that comparisons across multiple inspections are difficult to achieve.

In this project, the team aims at developing novel vision-based technologies for the systematic inspection of structures using micro aerial vehicles (MAVs), including

  • A vision-based localization in real-time to localize the MAV accurately in GPS-denied areas, in particular close to structures. The MAV concurrently and in real-time maps the structure in 3D for obstacle avoidance and path planning using the MAV’s on-board stereo vision sensors and its processing capabilities.
  • A semi-autonomous assistive MAV flight mode for live inspection and mapping of structures. While the operator navigates the MAV close to structures, the MAV autonomously avoids obstacles perceived with its sensors.
  • A utonomous MAV waypoint navigation for systematic image collection, referencing, analysis, and reinspection of structures.



Technical University of Munich



Read More