Planned intervention: On Wednesday April 3rd 05:30 UTC Zenodo will be unavailable for up to 2-10 minutes to perform a storage cluster upgrade.
Published October 6, 2021 | Version 1.0
Software Open

Code and Dataset for the paper "Learning High-Speed Flight in the Wild" (Science Robotics, 2021).

Description

Accompanying code and dataset for the paper "Learning High-Speed Flight in the Wild". Please check out the project webpage http://rpg.ifi.uzh.ch/AgileAutonomy.html for more information on our project. The file agile_autonomy_code.zip contains a readme for instruction on how to compile and use the code of this repository.

Abstract

Quadrotors are agile. Unlike most other machines, they can traverse extremely complex environments at high speeds. To date, only expert human pilots have been able to fully exploit their capabilities. Autonomous operation with on-board sensing and computation has been limited to low speeds. State-of-the-art methods generally separate the navigation problem into subtasks: sensing, mapping, and planning. While this approach has proven successful at low speeds, the separation it builds upon can be problematic for high-speed navigation in cluttered environments. Indeed, the subtasks are executed sequentially, leading to increased processing latency and a compounding of errors through the pipeline. Here we propose an end-to-end approach that can autonomously fly quadrotors through complex natural and man-made environments at high speeds, with purely onboard sensing and computation. The key principle is to directly map noisy sensory observations to collision-free trajectories in a receding-horizon fashion. This direct mapping drastically reduces processing latency and increases robustness to noisy and incomplete perception. The sensorimotor mapping is performed by a convolutional network that is trained exclusively in simulation via privileged learning: imitating an expert with access to privileged information. By simulating realistic sensor noise, our approach achieves zero-shot transfer from simulation to challenging real-world environments that were never experienced during training: dense forests, snow-covered terrain, derailed trains and collapsed buildings. Our work demonstrates that end-to-end policies trained in simulation enable high-speed autonomous flight through challenging environments, outperforming traditional obstacle avoidance pipelines.

Files

agile_autonomy_code.zip

Files (60.3 GB)

Name Size Download all
md5:6da1c6349f70734177ae7ff2f3d4d0a7
161.0 MB Preview Download
md5:24c0be8ed80d683979c7a7edada511a2
58.5 GB Download
md5:84cf92925970508d80598e61b3aaf0f3
1.7 GB Download