Informative Path Planning for Search and Rescue using a UAV

Target search in an obstacle filled environment is a practically relevant challenge in robotics that has a huge impact in the society. The wide range of applications include searching for victims in a search and rescue operation, detecting weeds in precision agriculture, patrolling borders for military and navy, automated census of endangered species in a forest etc. An efficient target search algorithm provides a data acquisition platform with least human intervention, thus improving the quality of life of humans. This thesis aims at introducing a general path planning algorithm for UAVs flying at different heights in an obstacle filled environment, searching for targets in the ground field. An adaptive informative path planning (IPP) algorithm is introduced that simultaneously trade off between area coverage, field of view, height dependent sensor performance and obstacle avoidance. It plans under uncertainties in the sensor measurements at varying heights, and is robust against wrong target detections. It generates an optimal fixed horizon plan in the form of a 3D minimum-snap trajectory that maximizes the information gain in minimum flight time by providing maximum area coverage, without any collision with the obstacles. The resulting planner is modular in terms of the mapping strategy, environment complexity, different target, changes in the sensor model and optimizer used. The planner is tested against varying environmental complexities, demonstrating its capability in handling a wide range of possible environments. The planner outperforms other planners like non-adaptive IPP planner, coverage planner and random sampling planner, by demonstrating the fastest decrease in map error while flying for a fixed time budget. A proof of concept for the algorithm is provided through real experiments by running the algorithm on a UAV flying inside a lab environment, searching for targets lying on the ground. All the targets were successfully found and mapped by the algorithm, demonstrating its applicability in a real-life target search problem.