Search

Integrating deep learning with the search for new electron-phonon superconductors represents a burgeoning field of research, where the primary challenge lies in the computational intensity of calculating the electron-phonon spectral function, $\alpha^2F(\omega)$, the essential ingredient of Midgal-Eliashberg theory of superconductivity. To overcome this challenge, we adopt a two-step approach. First, we compute $\alpha^2F(\omega)$ for 818 dynamically stable materials. We then train a deep-learning model to predict $\alpha^2F(\omega)$, using an unconventional training strategy to temper the model's overfitting, enhancing predictions. Specifically, we train a Bootstrapped Ensemble of Tempered Equivariant graph neural NETworks (BETE-NET), obtaining an MAE of 0.21, 45 K, and 43 K for the Eliashberg moments derived from $\alpha^2F(\omega)$: $\lambda$, $\omega_{\log}$, and $\omega_{2}$, respectively, yielding an MAE of 2.5 K for the critical temperature, $T_c$. Further, we incorporate domain knowledge of the site-projected phonon density of states to impose inductive bias into the model's node attributes and enhance predictions. This methodological innovation decreases the MAE to 0.18, 29 K, and 28 K, respectively, yielding an MAE of 2.1 K for $T_c$. We illustrate the practical application of our model in high-throughput screening for high-$T_c$ materials. The model demonstrates an average precision nearly five times higher than random screening, highlighting the potential of ML in accelerating superconductor discovery. BETE-NET accelerates the search for high-$T_c$ superconductors while setting a precedent for applying ML in materials discovery, particularly when data is limited., Comment: 12 pages, 5 figures, 1 table

Sampling-based model-predictive controllers have become a powerful optimization tool for planning and control problems in various challenging environments. In this paper, we show how the default choice of uncorrelated Gaussian distributions can be improved upon with the use of a colored noise distribution. Our choice of distribution allows for the emphasis on low frequency control signals, which can result in smoother and more exploratory samples. We use this frequency-based sampling distribution with Model Predictive Path Integral (MPPI) in both hardware and simulation experiments to show better or equal performance on systems with various speeds of input response., Comment: Published to RA-L

Modeling dynamics is often the first step to making a vehicle autonomous. While on-road autonomous vehicles have been extensively studied, off-road vehicles pose many challenging modeling problems. An off-road vehicle encounters highly complex and difficult-to-model terrain/vehicle interactions, as well as having complex vehicle dynamics of its own. These complexities can create challenges for effective high-speed control and planning. In this paper, we introduce a framework for multistep dynamics prediction that explicitly handles the accumulation of modeling error and remains scalable for sampling-based controllers. Our method uses a specially-initialized Long Short-Term Memory (LSTM) over a limited time horizon as the learned component in a hybrid model to predict the dynamics of a 4-person seating all-terrain vehicle (Polaris S4 1000 RZR) in two distinct environments. By only having the LSTM predict over a fixed time horizon, we negate the need for long term stability that is often a challenge when training recurrent neural networks. Our framework is flexible as it only requires odometry information for labels. Through extensive experimentation, we show that our method is able to predict millions of possible trajectories in real-time, with a time horizon of five seconds in challenging off road driving scenarios.

In this paper, we provide a generalized framework for Variational Inference-Stochastic Optimal Control by using thenon-extensive Tsallis divergence. By incorporating the deformed exponential function into the optimality likelihood function, a novel Tsallis Variational Inference-Model Predictive Control algorithm is derived, which includes prior works such as Variational Inference-Model Predictive Control, Model Predictive PathIntegral Control, Cross Entropy Method, and Stein VariationalInference Model Predictive Control as special cases. The proposed algorithm allows for effective control of the cost/reward transform and is characterized by superior performance in terms of mean and variance reduction of the associated cost. The aforementioned features are supported by a theoretical and numerical analysis on the level of risk sensitivity of the proposed algorithm as well as simulation experiments on 5 different robotic systems with 3 different policy parameterizations.

In this paper we propose a novel decision making architecture for Robust Model Predictive Path Integral control (RMPPI) and investigate its performance guarantees and applicability to off-road navigation. Key building blocks of the proposed architecture are an augmented state space representation of the system consisting of nominal and actual dynamics, a placeholder for different types of tracking controllers, a safety logic for nominal state propagation, and an importance sampling scheme that takes into account the capabilities of the underlying tracking control. Using these ingredients, we derive a bound on the free energy growth of the dynamical system which is a function of task constraint satisfaction level, the performance of the underlying tracking controller, and the sampling error of the stochastic optimization used within RMPPI. To validate the bound on free energy growth, we perform experiments in simulation using two types of tracking controllers, namely the iterative Linear Quadratic Gaussian and Contraction-Metric based control. We further demonstrate the applicability of RMPPI in real hardware using the GT AutoRally vehicle. Our experiments demonstrate that RMPPI outperforms MPPI and Tube-MPPI by alleviating issues of the aforementioned model predictive controllers related to either lack of robustness or excessive conservatism. RMPPI provides the best of the two worlds in terms of agility and robustness to disturbances., Comment: To be published in Robotics and Automation Letters

In this work, we present a method for obtaining an implicit objective function for vision-based navigation. The proposed methodology relies on Imitation Learning, Model Predictive Control (MPC), and an interpretation technique used in Deep Neural Networks. We use Imitation Learning as a means to do Inverse Reinforcement Learning in order to create an approximate cost function generator for a visual navigation challenge. The resulting cost function, the costmap, is used in conjunction with MPC for real-time control and outperforms other state-of-the-art costmap generators in novel environments. The proposed process allows for simple training and robustness to out-of-sample data. We apply our method to the task of vision-based autonomous driving in multiple real and simulated environments and show its generalizability.

Recently, vision-based control has gained traction by leveraging the power of machine learning. In this work, we couple a model predictive control (MPC) framework to a visual pipeline. We introduce deep optical flow (DOF) dynamics, which is a combination of optical flow and robot dynamics. Using the DOF dynamics, MPC explicitly incorporates the predicted movement of relevant pixels into the planned trajectory of a robot. Our implementation of DOF is memory-efficient, data-efficient, and computationally cheap so that it can be computed in real-time for use in an MPC framework. The suggested Pixel Model Predictive Control (PixelMPC) algorithm controls the robot to accomplish a high-speed racing task while maintaining visibility of the important features (gates). This improves the reliability of vision-based estimators for localization and can eventually lead to safe autonomous flight. The proposed algorithm is tested in a photorealistic simulation with a high-speed drone racing task.

Digitisation has made the return of recordings made by researchers in the past far more achievable than ever before. This technological advance, combined with the ethical and political imperative towards decolonising methodologies in Indigenous research, has resulted in considerable interest in ensuring that recordings of cultural value be returned to Indigenous communities. In this chapter, I reflect upon the fieldwork experience of returning archival song recordings concerning public aspects of male initiation ceremonies, known as akiw and anmanty, to Anmatyerr-speaking communities in the Northern Territory of Australia. Despite attenuation of song knowledge across the region, these songs continue to be sung at annual ritual events. Once these recordings were returned to these communities, Anmatyerr people quickly received them as important reiterations of their present-day socio-cultural expression. Evidently imbricated in a complex, ritually based form of complementary filiation and knowledge dissemination, these songs are shared and taught in a fragile and changing context of ceremonial practice. The account provided here offers insights into songs associated with arguably the most persistent and significant form of ceremonial practice in Central Australia, although sparsely documented in the Anmatyerr region. I also highlight the relational properties of song via their connections to place, Anengkerr ‘Dreaming’ and people and provide important insights into how these communities perceive the archiving and preservation of this material.

This paper deals with the original field diaries and notebooks of Walter Baldwin Spencer during his brief fieldwork endeavour amongst the Arabana of northern South Australia in 1903. The information recorded by Spencer reveals a relatively accurate, although abbreviated and fragmentary, assemblage of Arabana mythologies and language that can be compared with information recorded by Luise Hercus with Mick McLean and other Arabana and Wangkangurru people, over 60 years later. In this paper we describe and contextualise what is an overlooked episode in Spencer and Gillen’s fieldwork career, provide an analysis of their work with Arabana informants, and compare their findings with more recent ethnographic information collected in the latter half of the 20 th century. Interrogating this historical information and rereading it in light of far more recent and thorough research, we demonstrate the benefits of combining the sets of information from two radically different periods in Australian ethnography, linguistics and anthropology.

This paper analyses a speech delivered by Francis James Gillen during the opening stages of what is now regarded as one of the most significant ethnographic recording events in Australian history. Gillen's 'speech' at the 1896 Engwura festival provides a

Following reports of an increased incidence of amyotrophic lateral sclerosis (ALS) in U.S. veterans, we have conducted a high-density genome-wide association study (GWAS) of ALS outcome and survival time in a sample of U.S. veterans. We tested ∼1.3 million single nucleotide polymorphisms (SNPs) for association with ALS outcome in 442 incident Caucasian veteran cases diagnosed with definite or probable ALS and 348 Caucasian veteran controls. To increase power, we also included genotypes from 5909 publicly-available non-veteran controls in the analysis. In the survival analysis, we tested for association between SNPs and post-diagnosis survival time in 639 Caucasian veteran cases with definite or probable ALS. After this discovery phase, we performed follow-up genotyping of 299 SNPs in an independent replication sample of Caucasian veterans and non-veterans (ALS outcome: 183 cases and 961 controls; survival: 118 cases). Although no SNPs reached genome-wide significance in the discovery phase for either phenotype, three SNPs were statistically significant in the replication analysis of ALS outcome: rs6080539 (177 kb from PCSK2), rs7000234 (4 kb from ZNF704), and rs3113494 (13 kb from LOC100506746). Two SNPs located in genes that were implicated by previous GWA studies of ALS were marginally significant in the pooled analysis of discovery and replication samples: rs17174381 in DPP6 (p = 4.4×10(-4)) and rs6985069 near ELP3 (p = 4.8×10(-4)). Our results underscore the difficulty of identifying and convincingly replicating genetic associations with a rare and genetically heterogeneous disorder such as ALS, and suggest that common SNPs are unlikely to account for a substantial proportion of patients affected by this devastating disorder.

Following reports of an increased incidence of amyotrophic lateral sclerosis (ALS) in U.S. veterans, we have conducted a high-density genome-wide association study (GWAS) of ALS outcome and survival time in a sample of U.S. veterans. We tested ∼1.3 million single nucleotide polymorphisms (SNPs) for association with ALS outcome in 442 incident Caucasian veteran cases diagnosed with definite or probable ALS and 348 Caucasian veteran controls. To increase power, we also included genotypes from 5909 publicly-available non-veteran controls in the analysis. In the survival analysis, we tested for association between SNPs and post-diagnosis survival time in 639 Caucasian veteran cases with definite or probable ALS. After this discovery phase, we performed follow-up genotyping of 299 SNPs in an independent replication sample of Caucasian veterans and non-veterans (ALS outcome: 183 cases and 961 controls; survival: 118 cases). Although no SNPs reached genome-wide significance in the discovery phase for either phenotype, three SNPs were statistically significant in the replication analysis of ALS outcome: rs6080539 (177 kb from PCSK2), rs7000234 (4 kb from ZNF704), and rs3113494 (13 kb from LOC100506746). Two SNPs located in genes that were implicated by previous GWA studies of ALS were marginally significant in the pooled analysis of discovery and replication samples: rs17174381 in DPP6 (p = 4.4×10(-4)) and rs6985069 near ELP3 (p = 4.8×10(-4)). Our results underscore the difficulty of identifying and convincingly replicating genetic associations with a rare and genetically heterogeneous disorder such as ALS, and suggest that common SNPs are unlikely to account for a substantial proportion of patients affected by this devastating disorder.

Benthic macroinvertebrate and periphyton communities of streams draining four different land use types within four distinct geological types were sampled between December 1996 and January 1997. Catchment land use comprised either standing mature or logged exotic forest, native forest, or hill country pasture. The geological types of these catchments were either Mesozoic sandstone-greywacke, Pleistocene-greywacke, Tertiary mudstone, or limestone in origin. Pastoral stream invertebrate community structure was significantly different from that found in forested streams, with no clear distinction separating communities from standing exotic, logged exotic, and native forest sites. Pastoral communities were dominated by dipterans and trichopterans. while in contrast, macroinvertebrate communities in streams draining sandstone-greywacke catchments were dominated by ephemeropterans and plecopterans, showing a clear influence of catchment geology on benthic macroinvertebrate communities. This sandstone-greywacke effect appeared to be independent of land use. Periphyton biomass was greatest in pastoral and exotic sites, particularly those draining limestone catchments. High nutrient and conductivity levels, both of which are characteristic of limestone streams, appeared to override the effect of light restrictions on periphyton growth in exotic forest sites. Overall, both geology and land use played major roles in determining the structure of stream benthic communities, with factors such as altitude and stream temperature also important influences on these communities. In November and December 1997, nutrient, shade, and disturbance effects were examined in periphyton communities colonising artificial substrates. These substrates were left in the 8 forested Hawkes Bay streams for 28 days with disturbance treatment substrates being physically abraded every 7 days. Nutrients (N + P) were added to nutrient treatment substrates and polythene cloth was used to create an artificiall

This research was performed to determine the factors which affect the quality of situation awareness (SA) in civilian aircrew members. The recent popularity and increased investigation of SA has forced the research community to be very specific in modeling how it enhances decision-making in complex, dynamic environments. This research sought to better understand the effects of poor communication, high workload and time pressure on losses of SA for teams and individuals. Based upon Endsley's (1995a) model of SA and an analysis of aviation incident reports, it was found that 205 of the 590 incident reports investigated involved a loss in SA. This implies that SA is indeed a significant factor affecting aviation decision-making. Further, the results show that instances of poor communication and high workload occur in significantly higher proportions of team comprehension errors. These findings point to both the usefulness of Endsley's (1995a) model and the usefulness of using incident report data for the understanding of SA.