A Benchmark Comparison of Learned Control Policies for Agile Quadrotor Flight

02/22/2022
by   Elia Kaufmann, et al.
0

Quadrotors are highly nonlinear dynamical systems that require carefully tuned controllers to be pushed to their physical limits. Recently, learning-based control policies have been proposed for quadrotors, as they would potentially allow learning direct mappings from high-dimensional raw sensory observations to actions. Due to sample inefficiency, training such learned controllers on the real platform is impractical or even impossible. Training in simulation is attractive but requires to transfer policies between domains, which demands trained policies to be robust to such domain gap. In this work, we make two contributions: (i) we perform the first benchmark comparison of existing learned control policies for agile quadrotor flight and show that training a control policy that commands body-rates and thrust results in more robust sim-to-real transfer compared to a policy that directly specifies individual rotor thrusts, (ii) we demonstrate for the first time that such a control policy trained via deep reinforcement learning can control a quadrotor in real-world experiments at speeds over 45km/h.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/22/2022

User-Conditioned Neural Control Policies for Mobile Robotics

Recently, learning-based controllers have been shown to push mobile robo...
research
03/28/2018

Reinforcement learning for non-prehensile manipulation: Transfer from simulation to physical system

Reinforcement learning has emerged as a promising methodology for traini...
research
11/13/2016

CAD2RL: Real Single-Image Flight without a Single Real Image

Deep reinforcement learning has emerged as a promising and powerful tech...
research
09/18/2023

Contrastive Learning for Enhancing Robust Scene Transfer in Vision-based Agile Flight

Scene transfer for vision-based mobile robotics applications is a highly...
research
10/13/2017

Unsupervised Real-Time Control through Variational Empowerment

We introduce a methodology for efficiently computing a lower bound to em...
research
10/26/2018

Stability-certified reinforcement learning: A control-theoretic perspective

We investigate the important problem of certifying stability of reinforc...
research
01/17/2023

The SwaNNFlight System: On-the-Fly Sim-to-Real Adaptation via Anchored Learning

Reinforcement Learning (RL) agents trained in simulated environments and...

Please sign up or login with your details

Forgot password? Click here to reset