Despite its prevalence in neurosensory systems for pattern recognition, event detection, and learning, the effects of sensory adaptation (SA) are not explored in reservoir computing (RC). Monazomycin‐based biomolecular synapse (MzBS) devices that exhibit volatile memristance and short‐term plasticity with two strength‐dependent modes of response are studied: facilitation and facilitation‐then‐depression (i.e., SA). Their ability to perform RC tasks including digit recognition, nonlinear function learning, and aerodynamic gust classification via combination of model‐based device simulations and physical experiments where SA presence is controlled is studied. Simulations exhibiting moderate SA achieve significantly higher accuracy classifying a custom 5 × 5 binary digit set, with experimental validation achieving maximum testing accuracies of 90%. Classifications of the Modified National Institute of Standards and Technology (MNIST) handwritten digit dataset achieve a maximum testing accuracy of 94.34% in devices with SA. Fitting error of the Mackey–Glass time series is also significantly reduced by SA. Experimentally obtained pressure distributions representing gusts on an airfoil in a wind tunnel are classified by MzBS reservoirs. Reservoirs exhibiting SA achieve 100% accuracy, unlike MzBS reservoirs without SA and comparable static neural networks.

Forpractical considerations reinforcement learning has proven to be a difficult task outside of simulation when applied to a physical experiment. Here we derive an optional approach to model free reinforcement learning, achieved entirely online, through careful experimental design and algorithmic decision making. We design a reinforcement learning scheme to implement traditionally episodic algorithms for an unstable 1-dimensional mechanical environment. The training scheme is completely autonomous, requiring no human to be present throughout the learning process. We show that the pseudo-episodic technique allows for additional learning updates with off-policy actor-critic and experience replay methods. We show that including these additional updates between periods of traditional training episodes can improve speed and consistency of learning. Furthermore, we validate the procedure in experimental hardware. In the physical environment, several algorithm variants learned rapidly, each surpassing baseline maximum reward. The algorithms in this research are model free and use only information obtained by an onboard sensor during training.

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.

Unlike artificial intelligent systems based on computers, which must be programmed for specific tasks, the human brain can learn in real-time to create new tactics and adapt to complex, unpredictable environments. Computers embedded in artificial intelligent systems can execute arbitrary inference algorithms capable of outperforming humans at specific tasks. However, without real-time self-programming functionality, they must be preprogrammed by humans and will likely to fail in unpredictable environments beyond their preprogrammed domains. In this work, a Si-based synaptic resistor (synstor) was developed by integrating Al2Ox/TaOy materials to emulate biological synapses. The synstors were characterized, and their operation mechanism based on the charge stored in the oxygen vacancies in the Al2Ox material was simulated and analyzed, to understand the inference, learning, and memory functions of the synstors. A self-programming neuromorphic integrated circuit (SNIC) based on synstors was fabricated to execute inference and learning algorithms concurrently in real-time with an energy efficiency more than six-orders of magnitudes higher than those of standard digital computers. The SNIC dynamically modified its algorithm in a real-time learning process to control a morphing wing, thus successfully improving its lift-to-drag force ratio and recovering the wing from stall in complex aerodynamic environments. The synaptic resistor circuits can potentially circumvent the fundamental limitations of computers, thus providing a platform analogous to neurobiological network with real-time self-programming functionality for artificial intelligent systems.

Macro fiber composites (MFC) have proven useful as multifunctional material actuators for implementation in intelligent aerospace structures; however, due to nonlinear behaviors such as hysteresis and creep, incorporating sensor feedback is necessary to achieve sufficient control. In our work we use an antagonistic MFC unimorph system to produce a smooth trailing edge deflection in a morphing airfoil. In the past, piezoelectric flex sensors have been used to provide position feedback for the airfoil trailing edge, but these sensors also suffer from hysteresis. To achieve accurate position measurements from the flex sensors, we use time-series machine learning to model the relationship between flex voltage output and the true deflection. After testing offline, a long short-term memory (LSTM) neural network is implemented for inference on the hardware system and compared to a traditional linear model. True deflection information is obtained through external laser measurements, providing a context for comparing the accuracy of the mentioned state inference methods. Additionally, the sensor models are used in conjunction with a PD feedback controller to determine performance when controlling the aileron. Another difficulty in MFC actuator application is the change in performance under loading. Therefore, we perform final performance comparisons in a wind tunnel to simulate a realistic environment for the airfoil. We find the presented methods improve state inference performance over the traditional linear method, allowing for more accurate tip control under the aerodynamic loading.