skip to main content

Title: Deep reinforcement learning achieves multifunctional morphing airfoil control

Smooth camber morphing aircraft offer increased control authority and improved aerodynamic efficiency. Smart material actuators have become a popular driving force for shape changes, capable of adhering to weight and size constraints and allowing for simplicity in mechanical design. As a step towards creating uncrewed aerial vehicles (UAVs) capable of autonomously responding to flow conditions, this work examines a multifunctional morphing airfoil’s ability to follow commands in various flows. We integrated an airfoil with a morphing trailing edge consisting of an antagonistic pair of macro fiber composites (MFCs), serving as both skin and actuator, and internal piezoelectric flex sensors to form a closed loop composite system. Closed loop feedback control is necessary to accurately follow deflection commands due to the hysteretic behavior of MFCs. Here we used a deep reinforcement learning algorithm, Proximal Policy Optimization, to control the morphing airfoil. Two neural controllers were trained in a simulation developed through time series modeling on long short-term memory recurrent neural networks. The learned controllers were then tested on the composite wing using two state inference methods in still air and in a wind tunnel at various flow speeds. We compared the performance of our neural controllers to one using traditional position-derivative feedback control methods. Our experimental results validate that the autonomous neural controllers were faster and more accurate than traditional methods. This research shows that deep learning methods can overcome common obstacles for achieving sufficient modeling and control when implementing smart composite actuators in an autonomous aerospace environment.

more » « less
Award ID(s):
Author(s) / Creator(s):
 ;  ;  
Publisher / Repository:
SAGE Publications
Date Published:
Journal Name:
Journal of Composite Materials
Page Range / eLocation ID:
p. 721-736
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract

    This work presents a detector‐integrated two‐tier control architecture capable of identifying the presence of various types of cyber‐attacks, and ensuring closed‐loop system stability upon detection of the cyber‐attacks. Working with a general class of nonlinear systems, an upper‐tier Lyapunov‐based Model Predictive Controller (LMPC), using networked sensor measurements to improve closed‐loop performance, is coupled with lower‐tier cyber‐secure explicit feedback controllers to drive a nonlinear multivariable process to its steady state. Although the networked sensor measurements may be vulnerable to cyber‐attacks, the two‐tier control architecture ensures that the process will stay immune to destabilizing malicious cyber‐attacks. Data‐based attack detectors are developed using sensor measurements via machine‐learning methods, namely artificial neural networks (ANN), under nominal and noisy operating conditions, and applied online to a simulated reactor‐reactor‐separator process. Simulation results demonstrate the effectiveness of these detection algorithms in detecting and distinguishing between multiple classes of intelligent cyber‐attacks. Upon successful detection of cyber‐attacks, the two‐tier control architecture allows convenient reconfiguration of the control system to stabilize the process to its operating steady state.

    more » « less
  2. Creating soft robots with sophisticated, autonomous capabilities requires these systems to possess reliable, on-line proprioception of 3D configuration through integrated soft sensors. We present a framework for predicting a soft robot’s 3D configuration via deep learning using feedback from a soft, proprioceptive sensor skin. Our framework introduces a kirigami-enabled strategy for rapidly sensorizing soft robots using off-the-shelf materials, a general kinematic description for soft robot geometry, and an investigation of neural network designs for predicting soft robot configuration. Even with hysteretic, non-monotonic feedback from the piezoresistive sensors, recurrent neural networks show potential for predicting our new kinematic parameters and, thus, the robot’s configuration. One trained neural network closely predicts steady-state configuration during operation, though complete dynamic behavior is not fully captured. We validate our methods on a trunk-like arm with 12 discrete actuators and 12 proprioceptive sensors. As an essential advance in soft robotic perception, we anticipate our framework will open new avenues towards closed loop control in soft robotics. 
    more » « less
  3. Abstract

    Uncrewed aerial vehicles are integral to a smart city framework, but the dynamic environments above and within urban settings are dangerous for autonomous flight. Wind gusts caused by the uneven landscape jeopardize safe and effective aircraft operation. Birds rapidly reject gusts by changing their wing shape, but current gust alleviation methods for aircraft still use discrete control surfaces. Additionally, modern gust alleviation controllers challenge small uncrewed aerial vehicle power constraints by relying on extensive sensing networks and computationally expensive modeling. Here we show end-to-end deep reinforcement learning forgoing state inference to efficiently alleviate gusts on a smart material camber-morphing wing. In a series of wind tunnel gust experiments at the University of Michigan, trained controllers reduced gust impact by 84% from on-board pressure signals. Notably, gust alleviation using signals from only three pressure taps was statistically indistinguishable from using six pressure tap signals. By efficiently rejecting environmental perturbations, reduced-sensor fly-by-feel controllers open the door to small uncrewed aerial vehicle missions in cities.

    more » « less
  4. Machine learning driven image-based controllers allow robotic systems to take intelligent actions based on the visual feedback from their environment. Understanding when these controllers might lead to system safety violations is important for their integration in safety-critical applications and engineering corrective safety measures for the system. Existing methods leverage simulation-based testing (or falsification) to find the failures of vision-based controllers, i.e., the visual inputs that lead to closed-loop safety violations. However, these techniques do not scale well to the scenarios involving high-dimensional and complex visual inputs, such as RGB images. In this work, we cast the problem of finding closed-loop vision failures as a Hamilton-Jacobi (HJ) reachability problem. Our approach blends simulation-based analysis with HJ reachability methods to compute an approximation of the backward reachable tube (BRT) of the system, i.e., the set of unsafe states for the system under vision-based controllers. Utilizing the BRT, we can tractably and systematically find the system states and corresponding visual inputs that lead to closed-loop failures. These visual inputs can be subsequently analyzed to find the input characteristics that might have caused the failure. Besides its scalability to high-dimensional visual inputs, an explicit computation of BRT allows the proposed approach to capture non-trivial system failures that are difficult to expose via random simulations. We demonstrate our framework on two case studies involving an RGB image-based neural network controller for (a) autonomous indoor navigation, and (b) autonomous aircraft taxiing. 
    more » « less
  5. Textile-based compression devices are widely used in fields such as healthcare, astronautics, cosmetics, defense, and more. While traditional compression garments are only able to apply passive pressure on the body, there have been some efforts to integrate smart materials such as shape memory alloys (SMAs) to make compression garments active and controllable. However, despite the advances in this field, accurate control of applied pressure on the body due remains a challenge due to vast population-scale anthropometric variability and intra-subjects variability in tissue softness, even if the actuators themselves are fully characterized. In this study, we begin to address these challenges by developing a novel size-adjustable SMA-based smart tourniquet capable of producing a controllable pressure for circumferential applications. The developed prototype was tested on an inflatable pressure cuff wrapped around a rigid cylinder. The thermal activation of SMA coils was achieved through Joule heating, and a microcontroller and a programmable power supply are used to provide the input signal. To control the compression force, a closed-loop PID controller was implemented, and the performance of the system was evaluated in 5 different testing conditions for variable and cyclic compression levels. The experiments showed that the controlled system could follow the desired control pressure reference with a steady-state of 1 mmHg. The compression tourniquet is able to produce more than 33 mmHg with an average actuation rate of 0.19 mmHg/s. This is the first demonstration of accurate closed-loop control of an SMA-incorporated compression technology to the best of our knowledge. This paper enables new, dynamic systems with controllable activation and low-effort donning and doffing, with applications ranging from healthcare solutions to advanced spacesuit design. 
    more » « less