English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Purpose: Real-life applications using quadrotors introduce a number ofdisturbances and time-varying properties that pose a challenge to flightcontrollers. We observed that, when a quadrotor is tasked with picking up anddropping a payload, traditional PID and RL-based controllers found inliterature struggle to maintain flight after the vehicle changes its dynamicsdue to interaction with this external object.  Methods: In this work, we introduce domain randomization during the trainingphase of a low-level waypoint guidance controller based on Soft Actor-Critic.The resulting controller is evaluated on the proposed payload pick up and droptask with added disturbances that emulate real-life operation of the vehicle.  Results & Conclusion: We show that, by introducing a certain degree ofuncertainty in quadrotor dynamics during training, we can obtain a controllerthat is capable to perform the proposed task using a larger variation ofquadrotor parameters. Additionally, the RL-based controller outperforms atraditional positional PID controller with optimized gains in this task, whileremaining agnostic to different simulation parameters.

Designing a Robust Low-Level Agnostic Controller for a Quadrotor with Actor-Critic Reinforcement Learning