Public defence in Automation, Systems and Control Engineering, M.Sc. Issouf Ouattara

The title of the thesis: Mapping, tree detection, localization, and autonomous flight of unmanned aerial vehicles in forest applications 

Thesis defender: Issouf Ouattara
Opponent: Emeritus Professor Hajime Asama, The University of Tokyo, Japan
Custos: Prof. Arto Visala, Aalto University School of Electrical Engineering

Two forest management tasks that are important for healthy forest growth are the cleaning of seedling stands and the prevention of moose damage. These management tasks are still primarily done manually. They are time-consuming, labor-intensive, and likely to face a labor shortage in the near future. This thesis has two aims: (1) to develop approaches that use images collected by a UAV platform to support the semiautonomous cleaning of a seedling stand and (2) to develop methods that enable UAVs to autonomously and selectively spray a bio-based repellent to prevent moose damage. 

The first two articles of the thesis demonstrate the feasibility of UAV-assisted semiautonomous cleaning of seedling stands. They develop deep learning methods that are used to detect seedling trees in the images collected by a low-cost UAV platform, thereby creating a map of the seedling trees. A graph-based registration approach is developed to localize the forest cleaning machine within the map. A human-machine interface is also developed to incorporate the registration algorithm and to show in real-time the seedling trees and the cleaning tool to the machine operator. 

The last three articles of this thesis aim to develop an autonomous UAV for selective spraying. A pose-graph state estimation approach is developed, achieving accurate position, attitude, and consistent velocity estimates. A novel loop closure method using surface variation features is developed to correct the drift in pose estimation. A region-growing algorithm is developed to segment the individual seedling trees from the LiDAR point cloud. Finally, a path planning utilizing an octree data structure, and the informed RRT* approach is used to plan a collision-free path enabling the UAV to fly from the top of a tree to another. These approaches solely rely on IMU and LiDAR data; they are fully implemented on a single board computer onboard the UAV platform, and they achieve real-time performance. 

Several real-world experiments have been conducted to test the methods developed in this thesis, including the autonomous flight in a seedling forest stand. The approaches proposed in this thesis have the potential to reduce the cost of seedling forest cleaning, which can double with delays of more than two years. They also have the potential to save significant areas of seedling forest stands from ungulate browsing damage, which affects more than half a million hectares of forest available for wood supply in Finland.

Key words: forestry, autonomous systems, unmanned aerial vehicle, simultaneous localization and mapping, path planning, individual tree detection, LiDAR, IMU

Thesis available for public display 7 days prior to the defence at Aaltodoc. 

Contact: 
Email: ouatissouf01@gmail.com 
LinkedIn: https://www.linkedin.com/in/issoufouattara/
Research Group: https://www.aalto.fi/en/department-of-electrical-engineering-and-automation/autonomous-systems