Machine learning approaches have recently been leveraged as a substitute or an aid for physical/mathematical modeling approaches to dynamical systems. To develop an efficient machine learning method dedicated to modeling and prediction of multiscale dynamics, we propose a reservoir computing (RC) model with diverse timescales by using a recurrent network of heterogeneous leaky integrator (LI) neurons. We evaluate computational performance of the proposed model in two time series prediction tasks related to four chaotic fast-slow dynamical systems. In a one-step-ahead prediction task where input data are provided only from the fast subsystem, we show that the proposed model yields better performance than the standard RC model with identical LI neurons. Our analysis reveals that the timescale required for producing each component of target multiscale dynamics is appropriately and flexibly selected from the reservoir dynamics by model training. In a long-term prediction task, we demonstrate that a closed-loop version of the proposed model can achieve longer-term predictions compared to the counterpart with identical LI neurons depending on the hyperparameter setting.

In recent decades, climate change has significantly affected glacier dynamics, resulting in mass loss and an increased risk of glacier-related hazards including supraglacial and proglacial lake development, as well as catastrophic outburst flooding. Rapidly changing conditions dictate the need for continuous and detailed observations and analysis of climate-glacier dynamics. Thematic and quantitative information regarding glacier geometry is fundamental for understanding climate forcing and the sensitivity of glaciers to climate change, however, accurately mapping debris-cover glaciers (DCGs) is notoriously difficult based upon the use of spectral information and conventional machine-learning techniques. The objective of this research is to improve upon an earlier proposed deep-learning-based approach, GlacierNet, which was developed to exploit a convolutional neural-network segmentation model to accurately outline regional DCG ablation zones. Specifically, we developed an enhanced GlacierNet2 architecture thatincorporates multiple models, automatic post-processing, and basin-level hydrological flow techniques to improve the mapping of DCGs such that it includes both the ablation and accumulation zones. Experimental evaluations demonstrate that GlacierNet2 improves the estimation of the ablation zone and allows a high level of intersection over union (IOU: 0.8839) score. The proposed architecture provides complete glacier (both accumulation and ablation zone) outlines at regional scales, with an overall IOU score of 0.8619. This is a crucial first step in automating complete glacier mapping that can be used for accurate glacier modeling or mass-balance analysis.

Model Predictive Control (MPC) schemes have proven their efficiency in controlling high degree-of-freedom (DoF) complex robotic systems. However, they come at a high computational cost and an update rate of about tens of hertz. This relatively slow update rate hinders the possibility of stable haptic teleoperation of such systems since the slow feedback loops can cause instabilities and loss of transparency to the operator. This work presents a novel framework for transparent teleoperation of MPC-controlled complex robotic systems. In particular, we employ a feedback MPC approach and exploit its structure to account for the operator input at a fast rate which is independent of the update rate of the MPC loop itself. We demonstrate our framework on a mobile manipulator platform and show that it significantly improves haptic teleoperation's transparency and stability. We also highlight that the proposed feedback structure is constraint satisfactory and does not violate any constraints defined in the optimal control problem. To the best of our knowledge, this work is the first realization of the bilateral teleoperation of a legged manipulator using a whole-body MPC framework.

User modeling is crucial to understanding user behavior and essential for improving user experience and personalized recommendations. When users interact with software, vast amounts of command sequences are generated through logging and analytics systems. These command sequences contain clues to the users' goals and intents. However, these data modalities are highly unstructured and unlabeled, making it difficult for standard predictive systems to learn from. We propose SimCURL, a simple yet effective contrastive self-supervised deep learning framework that learns user representation from unlabeled command sequences. Our method introduces a user-session network architecture, as well as session dropout as a novel way of data augmentation. We train and evaluate our method on a real-world command sequence dataset of more than half a billion commands. Our method shows significant improvement over existing methods when the learned representation is transferred to downstream tasks such as experience and expertise classification.

Inverting seismic data to build 3D geological structures is a challenging task due to the overwhelming amount of acquired seismic data, and the very-high computational load due to iterative numerical solutions of the wave equation, as required by industry-standard tools such as Full Waveform Inversion (FWI). For example, in an area with surface dimensions of 4.5km $\times$ 4.5km, hundreds of seismic shot-gather cubes are required for 3D model reconstruction, leading to Terabytes of recorded data. This paper presents a deep learning solution for the reconstruction of realistic 3D models in the presence of field noise recorded in seismic surveys. We implement and analyze a convolutional encoder-decoder architecture that efficiently processes the entire collection of hundreds of seismic shot-gather cubes. The proposed solution demonstrates that realistic 3D models can be reconstructed with a structural similarity index measure (SSIM) of 0.8554 (out of 1.0) in the presence of field noise at 10dB signal-to-noise ratio.

This work presents a computationally lightweight motion planner for over-actuated platforms. For this purpose, a general state-space model for mobile platforms with several kinematic chains is defined, which considers non-linearities and constraints. The proposed motion planner is based on a sequential multi-stage approach that takes advantage of the warm start on each step. Firstly, a globally optimal and smooth 2D/3D trajectory is generated using the Fast Marching Method. This trajectory is fed as a warm start to a sequential linear quadratic regulator that is able to generate an optimal motion plan without constraints for all the platform actuators. Finally, a feasible motion plan is generated considering the constraints defined in the model. In this respect, the sequential linear quadratic regulator is employed again, taking the previously generated unconstrained motion plan as a warm start. This novel approach has been deployed into the Exomars Testing Rover of the European Space Agency. This rover is an Ackermann-capable planetary exploration testbed that is equipped with a robotic arm. Several experiments were carried out demonstrating that the proposed approach speeds up the computation time, increasing the success ratio for a martian sample retrieval mission, which can be considered as a representative use case of an over-actuated mobile platform.

Existing intelligent driving technology often has a problem in balancing smooth driving and fast obstacle avoidance, especially when the vehicle is in a non-structural environment, and is prone to instability in emergency situations. Therefore, this study proposed an autonomous obstacle avoidance control strategy that can effectively guarantee vehicle stability based on Attention-long short-term memory (Attention-LSTM) deep learning model with the idea of humanoid driving. First, we designed the autonomous obstacle avoidance control rules to guarantee the safety of unmanned vehicles. Second, we improved the autonomous obstacle avoidance control strategy combined with the stability analysis of special vehicles. Third, we constructed a deep learning obstacle avoidance control through experiments, and the average relative error of this system was 15%. Finally, the stability and accuracy of this control strategy were verified numerically and experimentally. The method proposed in this study can ensure that the unmanned vehicle can successfully avoid the obstacles while driving smoothly.

This paper proposes a novel approach to resilient distributed optimization with quadratic costs in a networked control system (e.g., wireless sensor network, power grid, robotic team) prone to external attacks (e.g., hacking, power outage) that cause agents to misbehave. Departing from classical filtering strategies proposed in literature, we draw inspiration from a game-theoretic formulation of the consensus problem and argue that adding competition to the mix can enhance resilience in the presence of malicious agents. Our intuition is corroborated by analytical and numerical results showing that i) our strategy highlights the presence of a nontrivial tradeoff between blind collaboration and full competition, and ii) such competition-based approach can outperform state-of-the-art algorithms based on Mean Subsequence Reduced.

The in situ synchrotron high-energy X-ray powder diffraction (XRD) technique is highly utilized by researchers to analyze the crystallographic structures of materials in functional devices (e.g., battery materials) or in complex sample environments (e.g., diamond anvil cells or syntheses reactors). An atomic structure of a material can be identified by its diffraction pattern, along with detailed analysis such as Rietveld refinement which indicates how the measured structure deviates from the ideal structure (e.g., internal stresses or defects). For in situ experiments, a series of XRD images is usually collected on the same sample at different conditions (e.g., adiabatic conditions), yielding different states of matter, or simply collected continuously as a function of time to track the change of a sample over a chemical or physical process. In situ experiments are usually performed with area detectors, collecting 2D images composed of diffraction rings for ideal powders. Depending on the material's form, one may observe different characteristics other than the typical Debye Scherrer rings for a realistic sample and its environments, such as textures or preferred orientations and single crystal diffraction spots in the 2D XRD image. In this work, we present an investigation of machine learning methods for fast and reliable identification and separation of the single crystal diffraction spots in XRD images. The exclusion of artifacts during an XRD image integration process allows a precise analysis of the powder diffraction rings of interest. We observe that the gradient boosting method can consistently produce high accuracy results when it is trained with small subsets of highly diverse datasets. The method dramatically decreases the amount of time spent on identifying and separating single crystal spots in comparison to the conventional method.

The production, shipping, usage, and disposal of consumer goods have a substantial impact on greenhouse gas emissions and the depletion of resources. Modern retail platforms rely heavily on Machine Learning (ML) for their search and recommender systems. Thus, ML can potentially support efforts towards more sustainable consumption patterns, for example, by accounting for sustainability aspects in product search or recommendations. However, leveraging ML potential for reaching sustainability goals requires data on sustainability. Unfortunately, no open and publicly available database integrates sustainability information on a product-by-product basis. In this work, we present the GreenDB, which fills this gap. Based on search logs of millions of users, we prioritize which products users care about most. The GreenDB schema extends the well-known schema.org Product definition and can be readily integrated into existing product catalogs to improve sustainability information available for search and recommendation experiences. We present our proof of concept implementation of a scraping system that creates the GreenDB dataset.