Showing papers by "Toyota published in 2020"

Understanding and applying coulombic efficiency in lithium metal batteries

Abstract: Coulombic efficiency (CE) has been widely used in battery research as a quantifiable indicator for the reversibility of batteries While CE helps to predict the lifespan of a lithium-ion battery, the prediction is not necessarily accurate in a rechargeable lithium metal battery Here, we discuss the fundamental definition of CE and unravel its true meaning in lithium-ion batteries and a few representative configurations of lithium metal batteries Through examining the similarities and differences of CE in lithium-ion batteries and lithium metal batteries, we establish a CE measuring protocol with the aim of developing high-energy long-lasting practical lithium metal batteries The understanding of CE and the CE protocol are broadly applicable in other rechargeable metal batteries including Zn, Mg and Na batteries Coulombic efficiency (CE) has been frequently used to assess the cyclability of newly developed materials for lithium metal batteries The authors argue that caution must be exercised during the assessment of CE, and propose a CE testing protocol for the development of lithium metal batteries

Closed-loop optimization of fast-charging protocols for batteries with machine learning.

Abstract: Simultaneously optimizing many design parameters in time-consuming experiments causes bottlenecks in a broad range of scientific and engineering disciplines1,2. One such example is process and control optimization for lithium-ion batteries during materials selection, cell manufacturing and operation. A typical objective is to maximize battery lifetime; however, conducting even a single experiment to evaluate lifetime can take months to years3-5. Furthermore, both large parameter spaces and high sampling variability3,6,7 necessitate a large number of experiments. Hence, the key challenge is to reduce both the number and the duration of the experiments required. Here we develop and demonstrate a machine learning methodology to efficiently optimize a parameter space specifying the current and voltage profiles of six-step, ten-minute fast-charging protocols for maximizing battery cycle life, which can alleviate range anxiety for electric-vehicle users8,9. We combine two key elements to reduce the optimization cost: an early-prediction model5, which reduces the time per experiment by predicting the final cycle life using data from the first few cycles, and a Bayesian optimization algorithm10,11, which reduces the number of experiments by balancing exploration and exploitation to efficiently probe the parameter space of charging protocols. Using this methodology, we rapidly identify high-cycle-life charging protocols among 224 candidates in 16 days (compared with over 500 days using exhaustive search without early prediction), and subsequently validate the accuracy and efficiency of our optimization approach. Our closed-loop methodology automatically incorporates feedback from past experiments to inform future decisions and can be generalized to other applications in battery design and, more broadly, other scientific domains that involve time-intensive experiments and multi-dimensional design spaces.

Balancing volumetric and gravimetric uptake in highly porous materials for clean energy

Abstract: A huge challenge facing scientists is the development of adsorbent materials that exhibit ultrahigh porosity but maintain balance between gravimetric and volumetric surface areas for the onboard storage of hydrogen and methane gas—alternatives to conventional fossil fuels. Here we report the simulation-motivated synthesis of ultraporous metal–organic frameworks (MOFs) based on metal trinuclear clusters, namely, NU-1501-M (M = Al or Fe). Relative to other ultraporous MOFs, NU-1501-Al exhibits concurrently a high gravimetric Brunauer−Emmett−Teller (BET) area of 7310 m2 g−1 and a volumetric BET area of 2060 m2 cm−3 while satisfying the four BET consistency criteria. The high porosity and surface area of this MOF yielded impressive gravimetric and volumetric storage performances for hydrogen and methane: NU-1501-Al surpasses the gravimetric methane storage U.S. Department of Energy target (0.5 g g−1) with an uptake of 0.66 g g−1 [262 cm3 (standard temperature and pressure, STP) cm−3] at 100 bar/270 K and a 5- to 100-bar working capacity of 0.60 g g−1 [238 cm3 (STP) cm−3] at 270 K; it also shows one of the best deliverable hydrogen capacities (14.0 weight %, 46.2 g liter−1) under a combined temperature and pressure swing (77 K/100 bar → 160 K/5 bar).

Feature Pyramid and Hierarchical Boosting Network for Pavement Crack Detection

Abstract: Pavement crack detection is a critical task for insuring road safety. Manual crack detection is extremely time-consuming. Therefore, an automatic road crack detection method is required to boost this progress. However, it remains a challenging task due to the intensity inhomogeneity of cracks and complexity of the background, e.g., the low contrast with surrounding pavements and possible shadows with a similar intensity. Inspired by recent advances of deep learning in computer vision, we propose a novel network architecture, named feature pyramid and hierarchical boosting network (FPHBN), for pavement crack detection. The proposed network integrates context information to low-level features for crack detection in a feature pyramid way, and it balances the contributions of both easy and hard samples to loss by nested sample reweighting in a hierarchical way during training. In addition, we propose a novel measurement for crack detection named average intersection over union (AIU). To demonstrate the superiority and generalizability of the proposed method, we evaluate it on five crack datasets and compare it with the state-of-the-art crack detection, edge detection, and semantic segmentation methods. The extensive experiments show that the proposed method outperforms these methods in terms of accuracy and generalizability. Code and data can be found in https://github.com/fyangneil/pavement-crack-detection .

3D Packing for Self-Supervised Monocular Depth Estimation

Abstract: Although cameras are ubiquitous, robotic platforms typically rely on active sensors like LiDAR for direct 3D perception. In this work, we propose a novel self-supervised monocular depth estimation method combining geometry with a new deep network, PackNet, learned only from unlabeled monocular videos. Our architecture leverages novel symmetrical packing and unpacking blocks to jointly learn to compress and decompress detail-preserving representations using 3D convolutions. Although self-supervised, our method outperforms other self, semi, and fully supervised methods on the KITTI benchmark. The 3D inductive bias in PackNet enables it to scale with input resolution and number of parameters without overfitting, generalizing better on out-of-domain data such as the NuScenes dataset. Furthermore, it does not require large-scale supervised pretraining on ImageNet and can run in real-time. Finally, we release DDAD (Dense Depth for Automated Driving), a new urban driving dataset with more challenging and accurate depth evaluation, thanks to longer-range and denser ground-truth depth generated from high-density LiDARs mounted on a fleet of self-driving cars operating world-wide.

A Review on Challenges and Successes in Atomic-Scale Design of Catalysts for Electrochemical Synthesis of Hydrogen Peroxide

Abstract: Hydrogen peroxide is a valuable chemical oxidant with a wide range of applications in a variety of industrial processes, especially in water sanitization. Electrochemical synthesis of hydrogen pero...

Spatio-Temporal Graph for Video Captioning With Knowledge Distillation

Abstract: Video captioning is a challenging task that requires a deep understanding of visual scenes. State-of-the-art methods generate captions using either scene-level or object-level information but without explicitly modeling object interactions. Thus, they often fail to make visually grounded predictions, and are sensitive to spurious correlations. In this paper, we propose a novel spatio-temporal graph model for video captioning that exploits object interactions in space and time. Our model builds interpretable links and is able to provide explicit visual grounding. To avoid unstable performance caused by the variable number of objects, we further propose an object-aware knowledge distillation mechanism, in which local object information is used to regularize global scene features. We demonstrate the efficacy of our approach through extensive experiments on two benchmarks, showing our approach yields competitive performance with interpretable predictions.

Self-Supervised Model Adaptation for Multimodal Semantic Segmentation

Abstract: Learning to reliably perceive and understand the scene is an integral enabler for robots to operate in the real-world. This problem is inherently challenging due to the multitude of object types as well as appearance changes caused by varying illumination and weather conditions. Leveraging complementary modalities can enable learning of semantically richer representations that are resilient to such perturbations. Despite the tremendous progress in recent years, most multimodal convolutional neural network approaches directly concatenate feature maps from individual modality streams rendering the model incapable of focusing only on the relevant complementary information for fusion. To address this limitation, we propose a mutimodal semantic segmentation framework that dynamically adapts the fusion of modality-specific features while being sensitive to the object category, spatial location and scene context in a self-supervised manner. Specifically, we propose an architecture consisting of two modality-specific encoder streams that fuse intermediate encoder representations into a single decoder using our proposed self-supervised model adaptation fusion mechanism which optimally combines complementary features. As intermediate representations are not aligned across modalities, we introduce an attention scheme for better correlation. In addition, we propose a computationally efficient unimodal segmentation architecture termed AdapNet++ that incorporates a new encoder with multiscale residual units and an efficient atrous spatial pyramid pooling that has a larger effective receptive field with more than $$10\,\times $$ fewer parameters, complemented with a strong decoder with a multi-resolution supervision scheme that recovers high-resolution details. Comprehensive empirical evaluations on Cityscapes, Synthia, SUN RGB-D, ScanNet and Freiburg Forest benchmarks demonstrate that both our unimodal and multimodal architectures achieve state-of-the-art performance while simultaneously being efficient in terms of parameters and inference time as well as demonstrating substantial robustness in adverse perceptual conditions.

High-power Mg batteries enabled by heterogeneous enolization redox chemistry and weakly coordinating electrolytes

Abstract: Magnesium batteries have long been pursued as potentially low-cost, high-energy and safe alternatives to Li-ion batteries. However, Mg2+ interacts strongly with electrolyte solutions and cathode materials, leading to sluggish ion dissociation and diffusion, and consequently low power output. Here we report a heterogeneous enolization chemistry involving carbonyl reduction (C=O↔C–O−), which bypasses the dissociation and diffusion difficulties, enabling fast and reversible redox processes. This kinetically favoured cathode is coupled with a tailored, weakly coordinating boron cluster-based electrolyte that allows for dendrite-free Mg plating/stripping at a current density of 20 mA cm−2. The combination affords a Mg battery that delivers a specific power of up to 30.4 kW kg−1, nearly two orders of magnitude higher than that of state-of-the-art Mg batteries. The cathode and electrolyte chemistries elucidated here propel the development of magnesium batteries and would accelerate the adoption of this low-cost and safe battery technology. Owing to sluggish Mg-ion dissociation and diffusion, Mg-based batteries have low power densities. Here the authors carry out rational designs for both the cathode and the electrolyte to enable ultrafast kinetics of a Mg metal battery.

It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction

Abstract: Human trajectory forecasting with multiple socially interacting agents is of critical importance for autonomous navigation in human environments, e.g., for self-driving cars and social robots. In this work, we present Predicted Endpoint Conditioned Network (PECNet) for flexible human trajectory prediction. PECNet infers distant trajectory endpoints to assist in long-range multi-modal trajectory prediction. A novel non-local social pooling layer enables PECNet to infer diverse yet socially compliant trajectories. Additionally, we present a simple "truncation-trick" for improving few-shot multi-modal trajectory prediction performance. We show that PECNet improves state-of-the-art performance on the Stanford Drone trajectory prediction benchmark by ~20.9% and on the ETH/UCY benchmark by ~40.8%. Project homepage: this https URL

It Is Not the Journey But the Destination: Endpoint Conditioned Trajectory Prediction

Abstract: Human trajectory forecasting with multiple socially interacting agents is of critical importance for autonomous navigation in human environments, e.g., for self-driving cars and social robots. In this work, we present Predicted Endpoint Conditioned Network (PECNet) for flexible human trajectory prediction. PECNet infers distant trajectory endpoints to assist in long-range multi-modal trajectory prediction. A novel non-local social pooling layer enables PECNet to infer diverse yet socially compliant trajectories. Additionally, we present a simple “truncation-trick” for improving diversity and multi-modal trajectory prediction performance. We show that PECNet improves state-of-the-art performance on the Stanford Drone trajectory prediction benchmark by \({\sim }20.9\%\) and on the ETH/UCY benchmark by \({\sim }40.8\%\) (Code available at project homepage: https://karttikeya.github.io/publication/htf/).

Efficient near-infrared light-emitting diodes based on quantum dots in layered perovskite

Abstract: Light-emitting diodes (LEDs) based on excitonic material systems, in which tightly bound photoexcited electron–hole pairs migrate together rather than as individual charge carriers, offer an attractive route to developing solution-processed, high-performance light emitters. Here, we demonstrate bright, efficient, excitonic infrared LEDs through the incorporation of quantum dots (QDs)1 into a low-dimensional perovskite matrix. We program the surface of the QDs to trigger fast perovskite nucleation to achieve homogeneous incorporation of QDs into the matrix without detrimental QD aggregation, as verified by in situ grazing incidence wide-angle X-ray spectroscopy. We tailor the distribution of the perovskites to drive balanced ultrafast excitonic energy transfer to the QDs. The resulting LEDs operate in the short-wavelength infrared region, an important regime for imaging and sensing applications, and exhibit a high external quantum efficiency of 8.1% at 980 nm at a radiance of up to 7.4 W Sr−1 m−2. Embedding perovskite quantum dots in perovskite leads to bright, efficient 980 nm LEDs with applications in imaging and sensing.

Semantically-Guided Representation Learning for Self-Supervised Monocular Depth

Abstract: Self-supervised learning is showing great promise for monocular depth estimation, using geometry as the only source of supervision. Depth networks are indeed capable of learning representations that relate visual appearance to 3D properties by implicitly leveraging category-level patterns. In this work we investigate how to leverage more directly this semantic structure to guide geometric representation learning, while remaining in the self-supervised regime. Instead of using semantic labels and proxy losses in a multi-task approach, we propose a new architecture leveraging fixed pretrained semantic segmentation networks to guide self-supervised representation learning via pixel-adaptive convolutions. Furthermore, we propose a two-stage training process to overcome a common semantic bias on dynamic objects via resampling. Our method improves upon the state of the art for self-supervised monocular depth prediction over all pixels, fine-grained details, and per semantic categories.

Band-bending induced passivation: high performance and stable perovskite solar cells using a perhydropoly(silazane) precursor

Abstract: Surface passivation of the perovskite photo absorber is a key factor to improve the photovoltaic performance. So far robust passivation strategies have not yet been revealed. Here, we demonstrate a successful passivation strategy which controls the Fermi-level of the perovskite surface by improving the surface states. Such Fermi-level control caused band-bending between the surface and bulk of the perovskite, which enhanced the hole-extraction from the absorber bulk to the HTM side. As an added benefit, the inorganic passivation layer improved the device light stability. By depositing a thick protection layer on the complete device, a remarkable waterproofing effect was obtained. As a result, an enhancement of VOC and the conversion efficiency from 20.5% to 22.1% was achieved. We revealed these passivation mechanisms and used perhydropoly(silazane) (PHPS) derived silica to control the perovskite surface states.

Securing Vehicle-to-Everything (V2X) Communication Platforms

Abstract: Modern vehicular wireless technology enables vehicles to exchange information at any time, from any place, to any network–forms the vehicle-to-everything (V2X) communication platforms. Despite benefits, V2X applications also face great challenges to security and privacy–a very valid concern since breaches are not uncommon in automotive communication networks and applications. In this survey, we provide an extensive overview of V2X ecosystem. We also review main security/privacy issues, current standardization activities and existing defense mechanisms proposed within the V2X domain. We then identified semantic gaps of existing security solutions and outline possible open issues.

Machine learning for continuous innovation in battery technologies

Abstract: Batteries, as complex materials systems, pose unique challenges for the application of machine learning. Although a shift to data-driven, machine learning-based battery research has started, new initiatives in academia and industry are needed to fully exploit its potential.

A Universal Machine Learning Algorithm for Large-Scale Screening of Materials

Abstract: Application of machine learning (ML) methods for the determination of the gas adsorption capacities of nanomaterials, such as metal-organic frameworks (MOF), has been extensively investigated over the past few years as a computationally efficient alternative to time-consuming and computationally demanding molecular simulations. Depending on the thermodynamic conditions and the adsorbed gas, ML has been found to provide very accurate results. In this work, we go one step further and we introduce chemical intuition in our descriptors by using the "type" of the atoms in the structure, instead of the previously used building blocks, to account for the chemical character of the MOF. ML predictions for the methane and carbon dioxide adsorption capacities of several tens of thousands of hypothetical MOFs are evaluated at various thermodynamic conditions using the random forest algorithm. For all cases examined, the use of atom types instead of building blocks leads to significantly more accurate predictions, while the number of MOFs needed for the training of the ML algorithm in order to achieve a specified accuracy can be reduced by an order of magnitude. More importantly, since practically there are an unlimited number of building blocks that materials can be made of but a limited number of atom types, the proposed approach is more general and can be considered as universal. The universality and transferability was proved by predicting the adsorption properties of a completely different family of materials after the training of the ML algorithm in MOFs.

Materials and technical innovations in 3D printing in biomedical applications

Abstract: 3D printing is a rapidly growing research area, which significantly contributes to major innovations in various fields of engineering, science, and medicine. Although the scientific advancement of 3D printing technologies has enabled the development of complex geometries, there is still an increasing demand for innovative 3D printing techniques and materials to address the challenges in building speed and accuracy, surface finish, stability, and functionality. In this review, we introduce and review the recent developments in novel materials and 3D printing techniques to address the needs of the conventional 3D printing methodologies, especially in biomedical applications, such as printing speed, cell growth feasibility, and complex shape achievement. A comparative study of these materials and technologies with respect to the 3D printing parameters will be provided for selecting a suitable application-based 3D printing methodology. Discussion of the prospects of 3D printing materials and technologies will be finally covered.

A Digital Twin Paradigm: Vehicle-to-Cloud Based Advanced Driver Assistance Systems

Abstract: Digital twin, an emerging representation of cyberphysical systems, has attracted increasing attentions very recently. It opens the way to real-time monitoring and synchronization of real-world activities with the virtual counterparts. In this study, we develop a digital twin paradigm using an advanced driver assistance system (ADAS) for connected vehicles. By leveraging vehicle-to-cloud (V2C) communication, on-board devices can upload the data to the server through cellular network. The server creates a virtual world based on the received data, processes them with the proposed models, and sends them back to the connected vehicles. Drivers can benefit from this V2C based ADAS, even if all computations are conducted on the cloud. The cooperative ramp merging case study is conducted, and the field implementation results show the proposed digital twin framework can benefit the transportation systems regarding mobility and environmental sustainability with acceptable communication delays and packet losses.

Random forest machine learning models for interpretable X-ray absorption near-edge structure spectrum-property relationships

Abstract: X-ray absorption spectroscopy (XAS) produces a wealth of information about the local structure of materials, but interpretation of spectra often relies on easily accessible trends and prior assumptions about the structure. Recently, researchers have demonstrated that machine learning models can automate this process to predict the coordinating environments of absorbing atoms from their XAS spectra. However, machine learning models are often difficult to interpret, making it challenging to determine when they are valid and whether they are consistent with physical theories. In this work, we present three main advances to the data-driven analysis of XAS spectra: we demonstrate the efficacy of random forests in solving two new property determination tasks (predicting Bader charge and mean nearest neighbor distance), we address how choices in data representation affect model interpretability and accuracy, and we show that multiscale featurization can elucidate the regions and trends in spectra that encode various local properties. The multiscale featurization transforms the spectrum into a vector of polynomial-fit features, and is contrasted with the commonly-used “pointwise” featurization that directly uses the entire spectrum as input. We find that across thousands of transition metal oxide spectra, the relative importance of features describing the curvature of the spectrum can be localized to individual energy ranges, and we can separate the importance of constant, linear, quadratic, and cubic trends, as well as the white line energy. This work has the potential to assist rigorous theoretical interpretations, expedite experimental data collection, and automate analysis of XAS spectra, thus accelerating the discovery of new functional materials.

On-the-Fly Active Learning of Interatomic Potentials for Large-Scale Atomistic Simulations

Abstract: The on-the-fly generation of machine-learning force fields by active-learning schemes attracts a great deal of attention in the community of atomistic simulations. The algorithms allow the machine to self-learn an interatomic potential and construct machine-learned models on the fly during simulations. State-of-the-art query strategies allow the machine to judge whether new structures are out of the training data set or not. Only when the machine judges the necessity of updating the data set with the new structures are first-principles calculations carried out. Otherwise, the yet available machine-learned model is used to update the atomic positions. In this manner, most of the first-principles calculations are bypassed during training, and overall, simulations are accelerated by several orders of magnitude while retaining almost first-principles accuracy. In this Perspective, after describing essential components of the active-learning algorithms, we demonstrate the power of the schemes by presenting recent applications.

Autolabeling 3D Objects With Differentiable Rendering of SDF Shape Priors

Abstract: We present an automatic annotation pipeline to recover 9D cuboids and 3D shapes from pre-trained off-the-shelf 2D detectors and sparse LIDAR data. Our autolabeling method solves an ill-posed inverse problem by considering learned shape priors and optimizing geometric and physical parameters. To address this challenging problem, we apply a novel differentiable shape renderer to signed distance fields (SDF), leveraged together with normalized object coordinate spaces (NOCS). Initially trained on synthetic data to predict shape and coordinates, our method uses these predictions for projective and geometric alignment over real samples. Moreover, we also propose a curriculum learning strategy, iteratively retraining on samples of increasing difficulty in subsequent self-improving annotation rounds. Our experiments on the KITTI3D dataset show that we can recover a substantial amount of accurate cuboids, and that these autolabels can be used to train 3D vehicle detectors with state-of-the-art results.

Benchmarking the acceleration of materials discovery by sequential learning.

Abstract: Sequential learning (SL) strategies, i.e. iteratively updating a machine learning model to guide experiments, have been proposed to significantly accelerate materials discovery and research. Applications on computational datasets and a handful of optimization experiments have demonstrated the promise of SL, motivating a quantitative evaluation of its ability to accelerate materials discovery, specifically in the case of physical experiments. The benchmarking effort in the present work quantifies the performance of SL algorithms with respect to a breadth of research goals: discovery of any “good” material, discovery of all “good” materials, and discovery of a model that accurately predicts the performance of new materials. To benchmark the effectiveness of different machine learning models against these goals, we use datasets in which the performance of all materials in the search space is known from high-throughput synthesis and electrochemistry experiments. Each dataset contains all pseudo-quaternary metal oxide combinations from a set of six elements (chemical space), the performance metric chosen is the electrocatalytic activity (overpotential) for the oxygen evolution reaction (OER). A diverse set of SL schemes is tested on four chemical spaces, each containing 2121 catalysts. The presented work suggests that research can be accelerated by up to a factor of 20 compared to random acquisition in specific scenarios. The results also show that certain choices of SL models are ill-suited for a given research goal resulting in substantial deceleration compared to random acquisition methods. The results provide quantitative guidance on how to tune an SL strategy for a given research goal and demonstrate the need for a new generation of materials-aware SL algorithms to further accelerate materials discovery.

The Dr Jekyll and Mr Hyde of lithium sulfur batteries

Abstract: Although the concept of a lithium–sulfur (Li–S) battery promises an energy density surpassing that of conventional Li-ion cells, prototype cells have lagged far behind. As research on Li–S has progressed, four limiting challenges for the sulfur electrode have now emerged that must be addressed to facilitate their realization, including slow lithium polysulfide deposition kinetics at low electrolyte/sulfur ratios, the lithium polysulfide shuttle, the low electrical conductivity of sulfur active material, and the cracking of solid electrolytes due to the repeated expansion and contraction of sulfur active material. Notably, the challenges of both slow deposition kinetics and the lithium polysulfide shuttle only arise when using sulfur active material with the most common electrolyte solvents used in Li–S cells: liquid ethereal mixtures, such as DOL:DME. Consequently, a reckoning of ether-based electrolytes is at hand, which has shifted research focus toward solid electrolytes and alternative sulfur-based active materials; however, these alternative strategies have their own challenges. Meanwhile, dendrite growth and insufficient coulombic efficiency still plague lithium metal electrodes in both liquid and solid electrolytes at relevant current densities. Many approaches to mitigate dendrite growth have been attempted, including artificial SEIs, nucleation aids, high surface area current collectors and solid electrolytes. Despite successes, further work is needed to attain a sufficient level of performance for lithium metal to be used in commercial Li–S cells. Herein we discuss the strengths and weaknesses of many proposed solutions to these challenges with an eye toward the ever-present goal of competing with conventional Li-ion energy densities.

Architectural Design Alternatives Based on Cloud/Edge/Fog Computing for Connected Vehicles

Abstract: As vehicles playing an increasingly important role in people’s daily life, requirements on safer and more comfortable driving experience have arisen. Connected vehicles (CVs) can provide enabling technologies to realize these requirements and have attracted widespread attentions from both academia and industry. These requirements ask for a well-designed computing architecture to support the Quality-of-Service (QoS) of CV applications. Computation offloading techniques, such as cloud, edge, and fog computing, can help CVs process computation-intensive and large-scale computing tasks. Additionally, different cloud/edge/fog computing architectures are suitable for supporting different types of CV applications with highly different QoS requirements, which demonstrates the importance of the computing architecture design. However, most of the existing surveys on cloud/edge/fog computing for CVs overlook the computing architecture design, where they (i) only focus on one specific computing architecture and (ii) lack discussions on benefits, research challenges, and system requirements of different architectural alternatives. In this article, we provide a comprehensive survey on different architectural design alternatives based on cloud/edge/fog computing for CVs. The contributions of this article are: (i) providing a comprehensive literature survey on existing proposed architectural design alternatives based on cloud/edge/fog computing for CVs, (ii) proposing a new classification of computing architectures based on cloud/edge/fog computing for CVs: computation-aided and computation-enabled architectures, (iii) presenting a holistic comparison among different cloud/edge/fog computing architectures for CVs based on functional requirements of CV systems, including advantages, disadvantages, and research challenges, (iv) presenting a holistic overview on the design of CV systems from both academia and industry perspectives, including activities in industry, functional requirements, service requirements, and design considerations, and (v) proposing several open research issues of designing cloud/edge/fog computing architectures for CVs.

An Efficient Approach to Fabricate Air-Stable Perovskite Solar Cells via Addition of a Self-Polymerizing Ionic Liquid.

Abstract: Despite the excellent photovoltaic properties achieved by perovskite solar cells at the laboratory scale, hybrid perovskites decompose in the presence of air, especially at high temperatures and in humid environments. Consequently, high-efficiency perovskites are usually prepared in dry/inert environments, which are expensive and less convenient for scale-up purposes. Here, a new approach based on the inclusion of an in situ polymerizable ionic liquid, 1,3-bis(4-vinylbenzyl)imidazolium chloride ([bvbim]Cl), is presented, which allows perovskite films to be manufactured under humid environments, additionally leading to a material with improved quality and long-term stability. The approach, which is transferrable to several perovskite formulations, allows efficiencies as high as 17% for MAPbI3 processed in air % relative humidity (RH) ≥30 (from an initial 15%), and 19.92% for FAMAPbI3 fabricated in %RH ≥50 (from an initial 17%), providing one of the best performances to date under similar conditions.

Spatiotemporal Relationship Reasoning for Pedestrian Intent Prediction

Abstract: Reasoning over visual data is a desirable capability for robotics and vision-based applications. Such reasoning enables forecasting the next events or actions in videos. In recent years, various models have been developed based on convolution operations for prediction or forecasting, but they lack the ability to reason over spatiotemporal data and infer the relationships of different objects in the scene. In this letter, we present a framework based on graph convolution to uncover the spatiotemporal relationships in the scene for reasoning about pedestrian intent. A scene graph is built on top of segmented object instances within and across video frames. Pedestrian intent, defined as the future action of crossing or not-crossing the street, is very crucial piece of information for autonomous vehicles to navigate safely and more smoothly. We approach the problem of intent prediction from two different perspectives and anticipate the intention-to-cross within both pedestrian-centric and location-centric scenarios. In addition, we introduce a new dataset designed specifically for autonomous-driving scenarios in areas with dense pedestrian populations: the Stanford-TRI Intent Prediction (STIP) dataset. Our experiments on STIP and another benchmark dataset show that our graph modeling framework is able to predict the intention-to-cross of the pedestrians with an accuracy of 79.10% on STIP and 79.28% on Joint Attention for Autonomous Driving (JAAD) dataset up to one second earlier than when the actual crossing happens. These results outperform baseline and previous work. Please refer to http://stip.stanford.edu/ for the dataset and code.

CO oxidation activity of non-reducible oxide-supported mass-selected few-atom Pt single-clusters.

Abstract: Platinum nanocatalysts play critical roles in CO oxidation, an important catalytic conversion process. As the catalyst size decreases, the influence of the support material on catalysis increases which can alter the chemical states of Pt atoms in contact with the support. Herein, we demonstrate that under-coordinated Pt atoms at the edges of the first cluster layer are rendered cationic by direct contact with the Al2O3 support, which affects the overall CO oxidation activity. The ratio of neutral to cationic Pt atoms in the Pt nanocluster is strongly correlated with the CO oxidation activity, but no correlation exists with the total surface area of surface-exposed Pt atoms. The low oxygen affinity of cationic Pt atoms explains this counterintuitive result. Using this relationship and our modified bond-additivity method, which only requires the catalyst–support bond energy as input, we successfully predict the CO oxidation activities of various sized Pt clusters on TiO2. Platinum nanocatalysts play critical roles in CO oxidation. Herein, the authors discover that under-coordinated Pt atoms at the edges of the first cluster layer are rendered cationic by direct contact with the Al2O3 support, which affects the overall CO oxidation activity.

Photocatalytic CO2 Reduction Using a Robust Multifunctional Iridium Complex toward the Selective Formation of Formic Acid.

Abstract: A highly efficient tetradentate PNNP-type Ir photocatalyst, Mes-IrPCY2, was developed for the reduction of carbon dioxide. The photocatalyst furnished formic acid (HCO2H) with 87% selectivity toget...