A Benchmark Comparison of Learned Control Policies for Agile Quadrotor Flight

by   Elia Kaufmann, et al.

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.


page 1

page 2

page 3

page 4


Sim-to-Real: Learning Agile Locomotion For Quadruped Robots

Designing agile locomotion for quadruped robots often requires extensive...

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

Reinforcement learning has emerged as a promising methodology for traini...

Unsupervised Real-Time Control through Variational Empowerment

We introduce a methodology for efficiently computing a lower bound to em...

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

Deep reinforcement learning has emerged as a promising and powerful tech...

Stability-certified reinforcement learning: A control-theoretic perspective

We investigate the important problem of certifying stability of reinforc...

Learning Event-triggered Control from Data through Joint Optimization

We present a framework for model-free learning of event-triggered contro...

NeuroBEM: Hybrid Aerodynamic Quadrotor Model

Quadrotors are extremely agile, so much in fact, that classic first-prin...