Learning Minimum-Time Flight in Cluttered Environments

TL;DR

This paper presents a deep reinforcement learning approach combined with topological path planning to enable quadrotors to fly minimum-time trajectories through cluttered environments with high robustness and a 100% success rate.

Contribution

It introduces a neural network controller that plans and controls minimum-time flight online, outperforming existing methods in robustness and success rate.

Findings

Neural network controller improves performance by up to 19% over state-of-the-art.

Achieves 100% collision-free minimum-time flight success rate.

Validated in simulation and real-world with speeds up to 42 km/h.

Abstract

We tackle the problem of minimum-time flight for a quadrotor through a sequence of waypoints in the presence of obstacles while exploiting the full quadrotor dynamics. Early works relied on simplified dynamics or polynomial trajectory representations that did not exploit the full actuator potential of the quadrotor, and, thus, resulted in suboptimal solutions. Recent works can plan minimum-time trajectories; yet, the trajectories are executed with control methods that do not account for obstacles. Thus, a successful execution of such trajectories is prone to errors due to model mismatch and in-flight disturbances. To this end, we leverage deep reinforcement learning and classical topological path planning to train robust neural-network controllers for minimum-time quadrotor flight in cluttered environments. The resulting neural network controller demonstrates substantially better performance of up to 19\% over state-of-the-art methods. More importantly, the learned policy solves the planning and control problem simultaneously online to account for disturbances, thus achieving much higher robustness. As such, the presented method achieves 100% success rate of flying minimum-time policies without collision, while traditional planning and control approaches achieve only 40%. The proposed method is validated in both simulation and the real world, with quadrotor speeds of up to 42km/h and accelerations of 3.6g.