A Sim-to-Real Deep Learning-based Framework for Autonomous Nano-drone Racing

TL;DR

This paper presents a novel onboard deep learning framework for autonomous nano-drone racing, trained solely in simulation, which successfully competed and won at the IMAV 2022 Nanocopter AI Challenge.

Contribution

It introduces a fully onboard sim-to-real deep learning system for nano-drone navigation, overcoming resource constraints and demonstrating real-world effectiveness in a competitive setting.

Findings

Won the IMAV 2022 Nanocopter AI Challenge

Achieved 115 meters of travel without crashing

Demonstrated effective sim-to-real transfer for nano-drones

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 ~10cm form factor heavily restricts the resources available onboard, including memory, computation, and sensors. This paper 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 1st among seven competing teams at the competition. In our best attempt, we scored 115m 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.