While there have been advancements in autonomous driving control and traffic simulation, there have been little to no works exploring their unification with deep learning. Works in both areas seem to focus on entirely different exclusive problems, yet traffic and driving are inherently related in the real world. In this paper, we present Traffic-Aware Autonomous Driving (TrAAD), a generalizable distillation-style method for traffic-informed imitation learning that directly optimizes for faster traffic flow and lower energy consumption. TrAAD focuses on the supervision of speed control in imitation learning systems, as most driving research focuses on perception and steering. Moreover, our method addresses the lack of co-simulation between traffic and driving simulators and provides a basis for directly involving traffic simulation with autonomous driving in future work. Our results show that, with information from traffic simulation involved in the supervision of imitation learning methods, an autonomous vehicle can learn how to accelerate in a fashion that is beneficial for traffic flow and overall energy consumption for all nearby vehicles.

This paper presents the Real-time Adaptive and Interpretable Detection (RAID) algorithm. The novel approach addresses the limitations of state-of-the-art anomaly detection methods for multivariate dynamic processes, which are restricted to detecting anomalies within the scope of the model training conditions. The RAID algorithm adapts to non-stationary effects such as data drift and change points that may not be accounted for during model development, resulting in prolonged service life. A dynamic model based on joint probability distribution handles anomalous behavior detection in a system and the root cause isolation based on adaptive process limits. RAID algorithm does not require changes to existing process automation infrastructures, making it highly deployable across different domains. Two case studies involving real dynamic system data demonstrate the benefits of the RAID algorithm, including change point adaptation, root cause isolation, and improved detection accuracy.

Convolutional neural networks have been widely applied to hyperspectral image classification. However, traditional convolutions can not effectively extract features for objects with irregular distributions. Recent methods attempt to address this issue by performing graph convolutions on spatial topologies, but fixed graph structures and local perceptions limit their performances. To tackle these problems, in this paper, different from previous approaches, we perform the superpixel generation on intermediate features during network training to adaptively produce homogeneous regions, obtain graph structures, and further generate spatial descriptors, which are served as graph nodes. Besides spatial objects, we also explore the graph relationships between channels by reasonably aggregating channels to generate spectral descriptors. The adjacent matrices in these graph convolutions are obtained by considering the relationships among all descriptors to realize global perceptions. By combining the extracted spatial and spectral graph features, we finally obtain a spectral-spatial graph reasoning network (SSGRN). The spatial and spectral parts of SSGRN are separately called spatial and spectral graph reasoning subnetworks. Comprehensive experiments on four public datasets demonstrate the competitiveness of the proposed methods compared with other state-of-the-art graph convolution-based approaches.

Deep learning has recently gained immense popularity in the Earth sciences as it enables us to formulate purely data-driven models of complex Earth system processes. Deep learning-based weather prediction (DLWP) models have made significant progress in the last few years, achieving forecast skills comparable to established numerical weather prediction (NWP) models with comparatively lesser computational costs. In order to train accurate, reliable, and tractable DLWP models with several millions of parameters, the model design needs to incorporate suitable inductive biases that encode structural assumptions about the data and modelled processes. When chosen appropriately, these biases enable faster learning and better generalisation to unseen data. Although inductive biases play a crucial role in successful DLWP models, they are often not stated explicitly and how they contribute to model performance remains unclear. Here, we review and analyse the inductive biases of six state-of-the-art DLWP models, involving a deeper look at five key design elements: input data, forecasting objective, loss components, layered design of the deep learning architectures, and optimisation methods. We show how the design choices made in each of the five design elements relate to structural assumptions. Given recent developments in the broader DL community, we anticipate that the future of DLWP will likely see a wider use of foundation models -- large models pre-trained on big databases with self-supervised learning -- combined with explicit physics-informed inductive biases that allow the models to provide competitive forecasts even at the more challenging subseasonal-to-seasonal scales.

A long-standing goal of machine-learning-based protein engineering is to accelerate the discovery of novel mutations that improve the function of a known protein. We introduce a sampling framework for evolving proteins in silico that supports mixing and matching a variety of unsupervised models, such as protein language models, and supervised models that predict protein function from sequence. By composing these models, we aim to improve our ability to evaluate unseen mutations and constrain search to regions of sequence space likely to contain functional proteins. Our framework achieves this without any model fine-tuning or re-training by constructing a product of experts distribution directly in discrete protein space. Instead of resorting to brute force search or random sampling, which is typical of classic directed evolution, we introduce a fast MCMC sampler that uses gradients to propose promising mutations. We conduct in silico directed evolution experiments on wide fitness landscapes and across a range of different pre-trained unsupervised models, including a 650M parameter protein language model. Our results demonstrate an ability to efficiently discover variants with high evolutionary likelihood as well as estimated activity multiple mutations away from a wild type protein, suggesting our sampler provides a practical and effective new paradigm for machine-learning-based protein engineering.

The continuous monitoring by drone swarms remains a challenging problem due to the lack of power supply and the inability of drones to land on uneven surfaces. Heterogeneous swarms, including ground and aerial vehicles, can support longer inspections and carry a higher number of sensors on board. However, their capabilities are limited by the mobility of wheeled and legged robots in a cluttered environment. In this paper, we propose a novel concept for autonomous inspection that we call SwarmGear. SwarmGear utilizes a heterogeneous swarm that investigates the environment in a leader-follower formation. The leader drone is able to land on rough terrain and traverse it by four compliant robotic legs, possessing both the functionalities of an aerial and mobile robot. To preserve the formation of the swarm during its motion, virtual impedance links were developed between the leader and the follower drones. We evaluated experimentally the accuracy of the hybrid leader drone's ground locomotion. By changing the step parameters, the optimal step configuration was found. Two types of gaits were evaluated. The experiments revealed low crosstrack error (mean of 2 cm and max of 4.8 cm) and the ability of the leader drone to move with a 190 mm step length and a 3 degree standard yaw deviation. Four types of drone formations were considered. The best formation was used for experiments with SwarmGear, and it showed low overall crosstrack error for the swarm (mean 7.9 cm for the type 1 gait and 5.1 cm for the type 2 gait). The proposed system can potentially improve the performance of autonomous swarms in cluttered and unstructured environments by allowing all agents of the swarm to switch between aerial and ground formations to overcome various obstacles and perform missions over a large area.

This paper presents the design and control of a ballbot drivetrain that aims to achieve high agility, minimal footprint, and high payload capacity while maintaining dynamic stability. Two hardware platforms and analytical models were developed to test design and control methodologies. The full-scale ballbot prototype (MiaPURE) was constructed using off-the-shelf components and designed to have agility, footprint, and balance similar to that of a walking human. The planar inverted pendulum testbed (PIPTB) was developed as a reduced-order testbed for quick validation of system performance. We then proposed a simple yet robust LQR-PI controller to balance and maneuver the ballbot drivetrain with a heavy payload. This is crucial because the drivetrain is often subject to high stiction due to elastomeric components in the torque transmission system. This controller was first tested in the PIPTB to compare with traditional LQR and cascaded PI-PD controllers, and then implemented in the ballbot drivetrain. The MiaPURE drivetrain was able to carry a payload of 60 kg, achieve a maximum speed of 2.3 m/s, and come to a stop from a speed of 1.4 m/s in 2 seconds in a selected translation direction. Finally, we demonstrated the omnidirectional movement of the ballbot drivetrain in an indoor environment as a payload-carrying robot and a human-riding mobility device. Our experiments demonstrated the feasibility of using the ballbot drivetrain as a universal mobility platform with agile movements, minimal footprint, and high payload capacity using our proposed design and control methodologies.

Scenario-based probabilistic forecasts have become vital for decision-makers in handling intermittent renewable energies. This paper presents a recent promising deep learning generative approach called denoising diffusion probabilistic models. It is a class of latent variable models which have recently demonstrated impressive results in the computer vision community. However, to our knowledge, there has yet to be a demonstration that they can generate high-quality samples of load, PV, or wind power time series, crucial elements to face the new challenges in power systems applications. Thus, we propose the first implementation of this model for energy forecasting using the open data of the Global Energy Forecasting Competition 2014. The results demonstrate this approach is competitive with other state-of-the-art deep learning generative models, including generative adversarial networks, variational autoencoders, and normalizing flows.

This paper presents a unified framework to translate between pairs of shape abstractions: Text Point Cloud Program. We propose Neural Shape Compiler to model the abstraction transformation as a conditional generation process. It converts 3D shapes of three abstract types into discrete shape code, transforms each shape code into code of other abstract types through the proposed ShapeCode Transformer, and decodes them to output the target shape abstraction. Point Cloud code is obtained in a class-agnostic way by the proposed PointVQVAE. On Text2Shape, ShapeGlot, ABO, Genre, and Program Synthetic datasets, Neural Shape Compiler shows strengths in Text = Point Cloud, Point Cloud = Text, Point Cloud = Program, and Point Cloud Completion tasks.

Provides technical support on complex and business critical projects related to wildfire mitigation, asset performance, and T&D Operations across six states. Leverages large quantities of data, such as weather, environmental, outage, vegetation, and grid attributes, to inform long term risk analysis and aid in decision making. Works alongside senior leadership to develop tools and analysis and inform the future of data driven decisions. Develops presentations for senior management and recommends and implements changes to meet company goals. Conduct complex research studies and technical analyses in areas of specialized data science to support company objectives and enable Transmission and Distribution Operations.