Header

UZH-Logo

Maintenance Infos

Learning Perception-Aware Agile Flight in Cluttered Environments


Song, Yunlong; Shi, Kexin; Penicka, Robert; Scaramuzza, Davide (2023). Learning Perception-Aware Agile Flight in Cluttered Environments. In: 2023 IEEE International Conference on Robotics and Automation, ICRA 2023, London, United Kingdom of Great Britain and Northern Ireland, 29 May 2023 - 2 June 2023. Institute of Electrical and Electronics Engineers, 1989-1995.

Abstract

Recently, neural control policies have outperformed existing model-based planning-and-control methods for autonomously navigating quadrotors through cluttered environments in minimum time. However, they are not perception aware, a crucial requirement in vision-based navigation due to the camera's limited field of view and the underactuated nature of a quadrotor. We propose a learning-based system that achieves perception-aware, agile flight in cluttered environments. Our method combines imitation learning with reinforcement learning (RL) by leveraging a privileged learning-by-cheating framework. Using RL, we first train a perception-aware teacher policy with full-state information to fly in minimum time through cluttered environments. Then, we use imitation learning to distill its knowledge into a vision-based student policy that only perceives the environment via a camera. Our approach tightly couples perception and control, showing a significant advantage in computation speed (10×faster) and success rate. We demonstrate the closed-loop control performance using hardware-in-the-loop simulation.

Abstract

Recently, neural control policies have outperformed existing model-based planning-and-control methods for autonomously navigating quadrotors through cluttered environments in minimum time. However, they are not perception aware, a crucial requirement in vision-based navigation due to the camera's limited field of view and the underactuated nature of a quadrotor. We propose a learning-based system that achieves perception-aware, agile flight in cluttered environments. Our method combines imitation learning with reinforcement learning (RL) by leveraging a privileged learning-by-cheating framework. Using RL, we first train a perception-aware teacher policy with full-state information to fly in minimum time through cluttered environments. Then, we use imitation learning to distill its knowledge into a vision-based student policy that only perceives the environment via a camera. Our approach tightly couples perception and control, showing a significant advantage in computation speed (10×faster) and success rate. We demonstrate the closed-loop control performance using hardware-in-the-loop simulation.

Statistics

Citations

Altmetrics

Downloads

6 downloads since deposited on 27 Feb 2024
6 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:03 Faculty of Economics > Department of Informatics
Dewey Decimal Classification:000 Computer science, knowledge & systems
Scopus Subject Areas:Physical Sciences > Software
Physical Sciences > Control and Systems Engineering
Physical Sciences > Electrical and Electronic Engineering
Physical Sciences > Artificial Intelligence
Scope:Discipline-based scholarship (basic research)
Language:English
Event End Date:2 June 2023
Deposited On:27 Feb 2024 16:01
Last Modified:28 Feb 2024 04:55
Publisher:Institute of Electrical and Electronics Engineers
Series Name:IEEE International Conference on Robotics and Automation. Proceedings
ISSN:1050-4729
ISBN:979-8-3503-2365-8
OA Status:Green
Publisher DOI:https://doi.org/10.1109/ICRA48891.2023.10160563
  • Content: Accepted Version
  • Language: English
  • Licence: Creative Commons: Attribution 4.0 International (CC BY 4.0)