Search

Resilience is a vital consideration for designing and operating a deep space habitat system. The numerous hazards that may affect a deep space habitat and its crew during its lifecycle need to be considered early in the design. Trade-off studies are the typical method used to assess the cost and value of different design choices. Here we develop a modular dynamic computational framework intended for rapid simulation and evaluation of the resilience of different system configurations. The framework uses a system-level phenomeno-logical Markov model of the habitat systems, enabling us to assess multiple habitat configurations and evaluate their performance in the presence of several hazards and user-defined control policies. System fault detection and repairs are modeled. External disturbances, including meteorites impact, temperature fluctuations, and dust, are modeled based on the lunar environment, envisioning a deep space habitat design. We use a reflexive health management subsystem that prioritizes recovery actions based on the robotic agent’s availability to close the loop. In addition to performance, a resilience metric is included to quantify the system’s resilience over the design lifecycle. We illustrate the use of the framework for supporting early-stage design decisions of a habitat system. Our case study focuses on designing the power generation system considering cost and energy efficiency.

Unmanned aerial vehicles, specifically quadrotor drones, are increasingly commonplace in community and workplace settings and are often used for photography, cinematography, and small parcel transport. The presence of these flying robotic systems has a substantial impact on the surrounding environment. To better understand the ergonomic impacts of quadrotor drones, a quantitative description of their acoustic signature is needed. While previous efforts have presented detailed acoustic characterizations, there is a distinct lack of high spatial-fidelity investigations of the acoustic field of a quadrotor hovering under its own power. This work presents an experimental quantification of the spatial acoustic pressure distribution in the near-field of a live hovering unmanned aerial vehicle. A large-aperture scanning microphone array was constructed to measure sound pressure level at a total of 1728 points over a 2 m × 3 m × 1.5 m volume. A physics-infused machine learning model was fit to the data to better visualize and understand the experimental results. The experimental data and modeling presented in this work are intended to inform future design of experiments for quadrotor drone acoustics, provide quantitative information on the acoustic near-field signature, and demonstrate the utility of optical motion tracking coupled with a custom microphone array for characterization of live acoustic sources.

Automated inverse design methods are critical to the development of metamaterial systems that exhibit special user-demanded properties. While machine learning approaches represent an emerging paradigm in the design of metamaterial structures, the ability to retrieve inverse designs on-demand remains lacking. Such an ability can be useful in accelerating optimization-based inverse design processes. This paper develops an inverse design framework that provides this capability through the novel usage of invertible neural networks (INNs). We exploit an INN architecture that can be trained to perform forward prediction over a set of high-fidelity samples and automatically learns the reverse mapping with guaranteed invertibility. We apply this INN for modeling the frequency response of periodic and aperiodic phononic structures, with the performance demonstrated on vibration suppression of drill pipes. Training and testing samples are generated by employing a transfer matrix method. The INN models provide competitive forward and inverse prediction performance compared to typical deep neural networks (DNNs). These INN models are used to retrieve approximate inverse designs for a queried non-resonant frequency range; the inverse designs are then used to initialize a constrained gradient-based optimization process to find a more accurate inverse design that also minimizes mass. The INN-initialized optimizations are found to be generally superior in terms of the queried property and mass compared to randomly initialized and inverse DNN-initialized optimizations. Particle swarm optimization with INN-derived initial points is then found to provide even better solutions, especially for the higher-dimensional aperiodic structures.

Aperiodic metamaterials represent a class of structural systems that are composed of different building blocks (cells), instead of a self-repeating chain of the same unit cells. Optimizing aperiodic cellular structural systems thus presents high-dimensional problems that are challenging to solve using purely high-fidelity structural optimization approaches. Specialized analytical modeling along with metamodel based optimization can provide a more tractable alternative solution approach. To this end, this paper presents a design automation framework applied to a 1D metamaterial system, namely a drill string, where vibration suppression is of utmost importance. The drill string comprises a set of nonuniform rings attached to the outer surface of a longitudinal rod. As such, the resultant system can now be perceived as an aperiodic 1D metamaterial with each ring/gap representing a cell. Despite being a 1D system, the simultaneous consideration of multiple DoF (i.e., torsional, axial, and lateral motions) poses significant computational challenges. Therefore, a transfer matrix method (TMM) is employed to analytically determine the frequency response of the drill string. A suite of neural networks (ANN) is trained on TMM samples (which present minute-scale computing costs per evaluation), to model the frequency response. ANN-based optimization is then performed to minimize mass subject to constraints on the gap between consecutive resonance peaks in one case, and minimizing this gap in the second case, leading to crucial improvements over baselines. Further novel contribution occurs through the development of an inverse modeling approach that can instantaneously produce the 1D metamaterial design with minimum mass for a given desired non-resonant frequency range. This is accomplished by using invertible neural networks, and results show promising alignment with forward solutions., Comment: Accepted for presentation in (and publication in the proceedings of) The ASME 2020 International Design Engineering Technical Conferences & Computers and Information in Engineering Conference (IDETC/CIE)

Locally resonant elastic metamaterials (LREM) can be designed, by optimizing the geometry of the constituent self-repeating unit cells, to potentially damp out vibration in selected frequency ranges, thus yielding desired bandgaps. However, it remains challenging to quickly arrive at unit cell designs that satisfy any requested bandgap specifications within a given global frequency range. This paper develops a computationally efficient framework for (fast) inverse design of LREM, by integrating a new type of machine learning models called invertible neural networks or INN. An INN can be trained to predict the bandgap bounds as a function of the unit cell design, and interestingly at the same time it learns to predict the unit cell design given a bandgap, when executed in reverse. In our case the unit cells are represented in terms of the width's of the outer matrix and middle soft filler layer of the unit cell. Training data on the frequency response of the unit cell is provided by Bloch dispersion analyses. The trained INN is used to instantaneously retrieve feasible (or near feasible) inverse designs given a specified bandgap constraint, which is then used to initialize a forward constrained optimization (based on sequential quadratic programming) to find the bandgap satisfying unit cell with minimum mass. Case studies show favorable performance of this approach, in terms of the bandgap characteristics and minimized mass, when compared to the median scenario over ten randomly initialized optimizations for the same specified bandgaps. Further analysis using FEA verify the bandgap performance of a finite structure comprised of $8\times 8$ arrangement of the unit cells obtained with INN-accelerated inverse design., Comment: Accepted to be presented and published in the Proceedings of the AIAA Aviation 2021 Forum

We introduce a novel machine learning-based fusion model termed as PI-LSTM (Physics-Infused Long Short-Term Memory Networks) that integrates first principle Physics-Based Models and Long Short-Term Memory (LSTM) network. Our architecture aims at combining equation-based models with data-driven machine learning models to enable accurate predictions of complex dynamic systems. In this hybrid architecture, recurrency aids the temporal memory of the inputs and output of the partial physics model, in a way that facilitates generalization with scarce data sets. We illustrate the application of PI-LSTM on two dynamical systems namely Inverted Pendulum and Tumor Growth. Empirical results on both test problems stand witness to the effectiveness of using physics in guiding machine learning models and the superiority of the outlined hybrid model over purely data-driven models.

Balance impairment is critical for many patient groups such as those with neural and musculoskeletal disorders and also the elderly. Accurate and objective assessment of balance performance has led to the development of several indices based on the measurement of the center of pressure. In this study, a robotic device was designed and fabricated to provide controlled and repeatable mechanical perturbations to the standing platform of the user. The device uses servo-controlled actuators and two parallel mechanisms to provide independent rotations in mediolateral and anterior-posterior directions. The device also provides visual feedback of the center of pressure position to the user. Functional tests were run and showed that the device is able to provide an appropriate dynamics (time constant of 0.19 s and bandwidth of 0.85 Hz) for the two motions. The efficacy of the device on the balance assessment was then evaluated experimentally. Ten healthy subjects performed a balance task with and without perturbations and seven center of pressure indices were measured. It was shown that the sensitivity of the indices to the user's performance was statistically increased in all indices particularly in anterior/posterior direction when the mechanical perturbations were present.

This paper presents the conceptual design and fabrication/assembly of an autonomous solar powered small unmanned ground vehicle (UGV) platform for operation in outdoor environments. The contribution lies in the ability of the proposed design to offer uninterrupted operation in terms of endurance, to facilitate educational and research applications that are otherwise challenging to perform with a typical UGV (that needs significant downtime for recharging). A high incident area for solar PV panels is required to be able to support the complete energy needs of a ∼ 46 lb UGV (i.e., fully recharge the suitably sized battery powering the UGV). This makes it challenging to develop a stable platform that can carry solar panels much larger than the surface area of the platform itself (an aspect receiving minimal attention in other similar purpose platforms). To address this challenge, a novel umbrella-like folding mechanism is conceived, designed and successfully incorporated in the baseline prototype. This mechanism allows incorporating a remarkable ∼1 sq.m of incident solar PV with a net rated capacity of 200 W, one that remains folded to facilitate mobility, and can open/unfold to different extents for energy capture when needed. At the same time, the proposed design facilitates static and dynamic stability in spite of the significant solar PV incorporation. With the reference of the baseline prototype, an optimization approach is taken to develop a conceptual design of the next generation of this solar UGV. Specifically, the incident angle of the solar panels (enabled by the umbrella mechanism) at complete-open stage and the dimensions of the mechanism links and associated supports are separately optimized to respectively maximize the energy capture and the range of the UGV (assuming operation in Buffalo, NY), subject to stability and nominal velocity (of 2km/hr) constraints. The optimum design is found to provide an estimated range of 19.8 km/day.

This paper focuses on the idea of energy efficient cooperative collision avoidance between two quadcopters. Two strategies for reciprocal online collision-avoiding actions (i.e., coherent maneuvers without requiring any real-time consensus) are proposed. In the first strategy, UAVs change their speed, while in the second strategy they change their heading to avoid a collision. The avoidance actions are parameterized in terms of the time difference between detecting the collision and starting the maneuver and the amount of speed/heading change. These action parameters are used to generate intermediate way-points, subsequently translated into a minimum snap trajectory, to be executed by a PD controller. For realism, the relative pose of the other UAV, estimated by each UAV (at the point of detection), is considered to be uncertain — thereby presenting substantial challenges to undertaking reciprocal actions. Performing supervised learning based on optimization derived labels (as done in prior work) becomes computationally burden-some under these uncertainties. Instead, an (unsupervised) neuroevolution algorithm, called AGENT, is employed to learn a neural network (NN) model that takes the initial (uncertain) pose as state inputs and maps it to a robust optimal action. In neuroevolution, the NN topology and weights are simultaneously optimized using a special evolutionary process, where the fitness of candidate NNs are evaluated over a set of sample (in this case, various collision) scenarios. For further computational tractability, a surrogate model is used to estimate the energy consumption and a classifier is used to identify trajectories where the controller fails. The trained neural network shows encouraging performance for collision avoidance over a large variety of unseen scenarios.

Cooperative autonomous approaches to avoiding collisions among small Unmanned Aerial Vehicles (UAVs) is central to safe integration of UAVs within the civilian airspace. One potential online cooperative approach is the concept of reciprocal actions, where both UAVs take pre-trained mutually coherent actions that do not require active online coordination (thereby avoiding the computational burden and risk associated with it). This paper presents a learning based approach to train such reciprocal maneuvers. Neuroevolution, which uses evolutionary algorithms to simultaneously optimize the topology and weights of neural networks, is used as the learning method -- which operates over a set of sample approach scenarios. Unlike most existing work (that minimize travel distance, energy or risk), the training process here focuses on the objective of minimizing the required detection range; this has important practical implications w.r.t. alleviating the dependency on sophisticated sensing and their reliability under various environments. A specialized design of experiments and line search is used to identify the minimum detection range for each sample scenarios. In order to allow an efficient training process, a classifier is used to discard actions (without simulating them) where the controller would fail. The model obtained via neuroevolution is observed to generalize well to (i.e., successful collision avoidance over) unseen approach scenarios., Accepted for presentation in (and publication in the proceedings of) 2019 AIAA AVIATION Forum and Exposition (2019 Air Traffic Operations, Management, and Systems Conference)

Neuroevolution is a process of training neural networks (NN) through an evolutionary algorithm, usually to serve as a state-to-action mapping model in control or reinforcement learning-type problems. This paper builds on the Neuro Evolution of Augmented Topologies (NEAT) formalism that allows designing topology and weight evolving NNs. Fundamental advancements are made to the neuroevolution process to address premature stagnation and convergence issues, central among which is the incorporation of automated mechanisms to control the population diversity and average fitness improvement within the neuroevolution process. Insights into the performance and efficiency of the new algorithm is obtained by evaluating it on three benchmark problems from the Open AI platform and an Unmanned Aerial Vehicle (UAV) collision avoidance problem., Accepted for presentation in (and publication in the proceedings of) the 2019 IEEE International Conference on Robotics and Automation (ICRA)

Hybrid modeling architectures seek to combine a machine learning model with a computationally efficient (simplified or partial) physics model to predict the behavior of physical systems. Existing sequential or parallel approaches to hybrid modeling do not typically exploit the potential relationship between the input or latent features of the partial and full physics. In addition, very few existing architectures take advantage of the provision to generously or on-demand sample the partial physics model. To address these gaps, we have developed a novel neural network-based hybrid architecture called “Opportunistic Physics-mining Transfer Mapping Architecture” or OPTMA. The goal of the OPTMA architecture is to facilitate greater exploitation of input space correlations between partial and full physics where they exist. To this end, a transfer neural network is used to transform the original inputs into modified inputs or latent features, where the partial physics operates on these artificially transformed features to produce the final prediction. An extended back-propagation approach and a Particle Swarm Optimization (to deal with multimodal loss functions) are used to train the network weights. The new architecture is first tested on a simple regression problem for analysis. It is then used to predict the behavior of more complex dynamic systems — an Inverted pendulum and the motion of an unmanned aerial vehicle, both under wind effects. Subsequent tests on unseen samples demonstrate OPTMA’s competitive performance compared to pure ANN and sequential hybrid models and provide empirical validation of the transfer concepts underlying OPTMA.

Majority of Artificial Neural Network (ANN) implementations in autonomous systems use a fixed/user-prescribed network topology, leading to sub-optimal performance and low portability. The existing neuro-evolution of augmenting topology or NEAT paradigm offers a powerful alternative by allowing the network topology and the connection weights to be simultaneously optimized through an evolutionary process. However, most NEAT implementations allow the consideration of only a single objective. There also persists the question of how to tractably introduce topological diversification that mitigates overfitting to training scenarios. To address these gaps, this paper develops a multi-objective neuro-evolution algorithm. While adopting the basic elements of NEAT, important modifications are made to the selection, speciation, and mutation processes. With the backdrop of small-robot path-planning applications, an experience-gain criterion is derived to encapsulate the amount of diverse local environment encountered by the system. This criterion facilitates the evolution of genes that support exploration, thereby seeking to generalize from a smaller set of mission scenarios than possible with performance maximization alone. The effectiveness of the single-objective (optimizing performance) and the multi-objective (optimizing performance and experience-gain) neuro-evolution approaches are evaluated on two different small-robot cases, with ANNs obtained by the multi-objective optimization observed to provide superior performance in unseen scenarios.