| Resumo: | Unmanned Aerial Vehicles (UAVs), although hardly a new technology, have recently gained a prominent role in many industries, being widely used not only among enthusiastic consumers but also in high demanding professional situations, and will have a massive societal impact over the coming years. However, the operation of UAVs is full of serious safety risks, such as collisions with dynamic obstacles (birds, other UAVs, or randomly thrown objects). These collision scenarios are complex to analyze in real-time, sometimes being computationally impossible to solve with existing State of the Art (SoA) algorithms, making the use of UAVs an operational hazard and therefore significantly reducing their commercial applicability in urban environments. In this work, a conceptual framework for both stand-alone and swarm (networked) UAVs is introduced, focusing on the architectural requirements of the collision avoidance subsystem to achieve acceptable levels of safety and reliability. First, the SoA principles for collision avoidance against stationary objects are reviewed. Afterward, a novel image processing approach that uses deep learning and optical flow is presented. This approach is capable of detecting and generating escape trajectories against potential collisions with dynamic objects. Finally, novel models and algorithms combinations were tested, providing a new approach for the collision avoidance of UAVs using Deep Neural Networks. The feasibility of the proposed approach was demonstrated through experimental tests using a UAV, created from scratch using the framework developed.
|
|---|