A Sim-to-Real Deep Learning-Based Framework for Autonomous Nano-Drone Racing
Lorenzo Lamberti, Elia Cereda, Gabriele Abbate, Lorenzo Bellone, Victor Javier Kartsch Morinigo, Michał Barciś, Agata Barciś, Alessandro Giusti, Francesco Conti, Daniele Palossi
Abstract
Autonomous drone racing competitions are a proxy to improve unmanned aerial vehicles' perception, planning, and control skills. The recent emergence of autonomous nano-sized drone racing imposes new challenges, as their <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\sim$</tex-math></inline-formula> <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\text{10} \,\text{c}\text{m}$</tex-math></inline-formula> form factor heavily restricts the resources available onboard, including memory, computation, and sensors. This letter describes the methodology and technical implementation of the system winning the first autonomous nano-drone racing international competition: the “IMAV 2022 Nanocopter AI Challenge.” We developed a fully onboard deep learning approach for visual navigation trained only on simulation images to achieve this goal. Our approach includes a convolutional neural network for obstacle avoidance, a sim-to-real dataset collection procedure, and a navigation policy that we selected, characterized, and adapted through simulation and actual in-field experiments. Our system ranked <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$1\text{st}$</tex-math></inline-formula> among six competing teams at the competition. In our best attempt, we scored <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\text{115} \,\text{m}$</tex-math></inline-formula> of traveled distance in the allotted 5-minute flight, never crashing while dodging static and dynamic obstacles. Sharing our knowledge with the research community, we aim to provide a solid groundwork to foster future development in this field.