Reinforcement Learning to Control Lift Coefficient Using Distributed Sensors on a Wind Tunnel Model

Abstract

Arrays of sensors distributed on the wing of fixed-wing vehicles can provide information not directly available to conventional sensor suites. These arrays of sensors have the potential to improve flight control and overall flight performance of small fixed-wing uninhabited aerial vehicles (UAVs). This work investigated the feasibility of estimating and controlling aerodynamic coefficients using the experimental readings of distributed pressure and strain sensors across a wing. The study was performed on a one degree-of-freedom model about pitch of a fixed-wing platform instrumented with the distributed sensing system. A series of reinforcement learning (RL) agents were trained in simulation for lift coefficient control, then validated in wind tunnel experiments. The performance of RL-based controllers with different sets of inputs in the observation space were compared with each other and with that of a manually tuned PID controller. Results showed that hybrid RL agents that used both distributed sensing data and conventional sensors performed best across the different tests.

Wind tunnel testing of an avian-inspired morphing wing with distributed pressure sensing

“…As implemented in this study, wing sweep produces considerable changes in pitching moment, particularly at high angles of attack. However, the changes to pitching moment produced by wing sweep δ w are not as large as those produced by conventional tail elevators, being roughly one order of magnitude lower than typical conventional small UAV configurations [31], [32]. Thus, wing sweep may not be suitable for fully replacing conventional tail elevators.…”

Deep Reinforcement Learning: A New Beacon for Intelligent Active Flow Control

“…The DRL agent can find a valid control policy with energy conservation by 83% under a combination of two different frequencies of inlet velocity. Guerra-Langan et al [76] trained a series of reinforcement learning (RL) agents in simulation for lift coefficient control, then validated them in wind tunnel experiments. Specifically, an ANN aerodynamic coefficients estimator is trained to estimate lift and drag coefficients using pressure and strain sensor readings together with pitch rate.…”