Implementation of Decentralized Reinforcement Learning-Based Multi-Quadrotor Flocking
Document Type
Article
Publication Date
1-1-2021
Abstract
Enabling coordinated motion of multiple quadrotors is an active area of research in the field of small unmanned aerial vehicles (sUAVs). While there are many techniques found in the literature that address the problem, these studies are limited to simulation results and seldom account for wind disturbances. This paper presents the experimental validation of a decentralized planner based on multi-objective reinforcement learning (RL) that achieves waypoint-based flocking (separation, velocity alignment, and cohesion) for multiple quadrotors in the presence of wind gusts. The planner is learned using an object-focused, greatest mass, state-action-reward-state-action (OF-GM-SARSA) approach. The Dryden wind gust model is used to simulate wind gusts during hardware-in-the-loop (HWIL) tests. The hardware and software architecture developed for the multi-quadrotor flocking controller is described in detail. HWIL and outdoor flight tests results show that the trained RL planner can generalize the flocking behaviors learned in training to the real-world flight dynamics of the DJI M100 quadrotor in windy conditions.
Identifier
85115758879 (Scopus)
Publication Title
IEEE Access
External Full Text Location
https://doi.org/10.1109/ACCESS.2021.3115711
e-ISSN
21693536
First Page
132491
Last Page
132507
Volume
9
Recommended Citation
Abichandani, Pramod; Speck, Christian; Bucci, Donald; McIntyre, William; and Lobo, Deepan, "Implementation of Decentralized Reinforcement Learning-Based Multi-Quadrotor Flocking" (2021). Faculty Publications. 4525.
https://digitalcommons.njit.edu/fac_pubs/4525