Searcharxiv⌕ Search

arXiv subjects

Xuesong Wang

Publications and source records attributed to Xuesong Wang.

At least 37 records · Page 2Linked to original sources

CookBench: A Long-Horizon Embodied Planning Benchmark for Complex Cooking Scenarios

Embodied Planning is dedicated to the goal of creating agents capable of executing long-horizon tasks in complex physical worlds. However, existing embodied planning benchmarks frequently feature short-horizon tasks and coarse-grained action primitives. To address this challenge, we introduce CookBench, a benchmark for long-horizon planning in complex cooking scenarios. By leveraging a high-fidelity simulation environment built upon the powerful Unity game engine, we define frontier AI challenges in a complex, realistic environment. The core task in CookBench is designed as a two-stage process. First, in Intention Recognition, an agent needs to accurately parse a user's complex intent. Second, in Embodied Interaction, the agent should execute the identified cooking goal through a long-horizon, fine-grained sequence of physical actions. Unlike existing embodied planning benchmarks, we refine the action granularity to a spatial level that considers crucial operational information while abstracting away low-level robotic control. Besides, We provide a comprehensive toolset that encapsulates the simulator. Its unified API supports both macro-level operations, such as placing orders and purchasing ingredients, and a rich set of fine-grained embodied actions for physical interaction, enabling researchers to focus on high-level planning and decision-making. Furthermore, we present an in-depth analysis of state-of-the-art, closed-source Large Language Model and Vision-Language Model, revealing their major shortcomings and challenges posed by complex, long-horizon tasks. The full benchmark will be open-sourced to facilitate future research.

cs.RO↗

Simultaneous Super-Resolution of Spatial and Spectral Imaging with a Camera Array and Notch Filters

This study proposes an algorithm based on a notch filter camera array system for simultaneous super-resolution imaging and spectral reconstruction, enhancing the spatial resolution and multispectral imaging capabilities of targets. In this study, multi-aperture super-resolution algorithms, pan-sharpening techniques, and spectral reconstruction algorithms were investigated and integrated. The sub-pixel level offset information and spectral disparities among the 9 low-resolution images captured by the 9 distinct imaging apertures were utilized, leading to the successful reconstruction of 31 super-resolution spectral images. By conducting simulations with a publicly available dataset and performing qualitative and quantitative comparisons with snapshot coded aperture spectral imaging systems, the experimental results demonstrate that our system and algorithm attained a peak signal-to-noise ratio of 35.6dB, representing a 5dB enhancement over the most advanced snapshot coded aperture spectral imaging systems, while also reducing processing time. This research offers an effective solution for achieving high temporal, spectral, and spatial resolution through the utilization of multi-aperture imaging systems.

eess.IV↗

Integrating Cascade Pumped Micro-Hydro Storage: A Sustainable Approach to Energy and Water Management

As traditional large hydropower has been extensively exploited, micro-hydro systems have caught research increasing interest. New engineering challenges arise in developing micro-hydro systems in areas with significant elevation but prohibitive horizontal distances between primary reservoirs. This study addresses these challenges by proposing a cascade-pumped micro-hydro storage (CPMHS) system that leverages intermediate reservoirs to bridge long horizontal distances, enabling efficient energy transfer and storage. The methodology utilizes naturally occurring lakes with substantial head heights but limited feasibility for direct pumped storage due to horizontal separations. Integrating smaller, strategically placed intermediate reservoirs maximizes energy capture along the cascading path, making pumped storage viable in geographically constrained locations. The proposed system will enhance energy generation potential and provide additional benefits for water management. Using geographical data and a detailed case study focused on Mountain Lake and surrounding lakes, this paper demonstrates the energy efficiency and viability of cascade-based micro-hydro storage. A practical methodology for implementing CPMHS systems is proposed and validated by case studies. An optimization framework is developed for efficient energy capture in regions with challenging topography.

eess.SY↗

Rényi Neural Processes

Neural Processes (NPs) are deep probabilistic models that represent stochastic processes by conditioning their prior distributions on a set of context points. Despite their advantages in uncertainty estimation for complex distributions, NPs enforce parameterization coupling between the conditional prior model and the posterior model. We show that this coupling amounts to prior misspecification and revisit the NP objective to address this issue. More specifically, we propose Rényi Neural Processes (RNP), a method that replaces the standard KL divergence with the Rényi divergence, dampening the effects of the misspecified prior during posterior updates. We validate our approach across multiple benchmarks including regression and image inpainting tasks, and show significant performance improvements of RNPs in real-world problems. Our extensive experiments show consistently better log-likelihoods over state-of-the-art NP models.

cs.LG↗

Characteristics Analysis of Autonomous Vehicle Pre-crash Scenarios

To date, hundreds of crashes have occurred in open road testing of automated vehicles (AVs), highlighting the need for improving AV reliability and safety. Pre-crash scenario typology classifies crashes based on vehicle dynamics and kinematics features. Building on this, characteristics analysis can identify similar features under comparable crashes, offering a more effective reflection of general crash patterns and providing more targeted recommendations for enhancing AV performance. However, current studies primarily concentrated on crashes among conventional human-driven vehicles, leaving a gap in research dedicated to in-depth AV crash analyses. In this paper, we analyzed the latest California AV collision reports and used the newly revised pre-crash scenario typology to identify pre-crash scenarios. We proposed a set of mapping rules for automatically extracting these AV pre-crash scenarios, successfully identifying 24 types with a 98.1% accuracy rate, and obtaining two key scenarios of AV crashes (i.e., rear-end scenarios and intersection scenarios) through detailed analysis. Association analyses of rear-end scenarios showed that the significant environmental influencing factors were traffic control type, location type, light, etc. For intersection scenarios prone to severe crashes with detailed descriptions, we employed causal analyses to obtain the significant causal factors: habitual violations and expectations of certain behavior. Optimization recommendations were then formulated, addressing both governmental oversight and AV manufacturers' potential improvements. The findings of this paper could guide government authorities to develop related regulations, help manufacturers design AV test scenarios, and identify potential shortcomings in control algorithms specific to various real-world scenarios, thereby optimizing AV systems effectively.

cs.RO↗

Graph-based Simulation Framework for Power Resilience Estimation and Enhancement

The increasing frequency of extreme weather events poses significant risks to power distribution systems, leading to widespread outages and severe economic and social consequences. This paper presents a novel simulation framework for assessing and enhancing the resilience of power distribution networks under such conditions. Resilience is estimated through Monte Carlo simulations, which simulate extreme weather scenarios and evaluate the impact on infrastructure fragility. Due to the proprietary nature of power network topology, a distribution network is synthesized using publicly available data. To generate the weather scenarios, an extreme weather generation method is developed. To enhance resilience, renewable resources such as solar panels and energy storage systems (batteries in this study) are incorporated. A customized Genetic Algorithm is proposed to determine the optimal locations and capacities for solar panels and battery installations, maximizing resilience while balancing cost constraints. Experiment results demonstrate that on a large-scale synthetic distribution network with more than 300,000 nodes and 300,000 edges, the proposed framework can efficiently evaluate the resilience, and enhance the resilience through the installations of distributed energy resources (DERs), providing utilities with valuable insights for community-level power system resilience estimation and enhancement.

eess.SY↗

Unlocking the Potential: A Novel Tool for Assessing Untapped Micro-Pumped Hydro Energy Storage Systems in Michigan

This study presents an innovative tool designed to unlock the potential of Michigan's lakes and dams for applications such as water resource management and renewable energy generation. Given Michigan's relatively flat landscape, the focus is on systems that could serve as micro-hydro energy storage solutions. To ensure accuracy and reliability, the tool incorporates extensive data gathered from authorized sources, covering more than 420 water facilities and potential reservoirs in the state. These data are used as part of a case study to evaluate the tool's capabilities. Key parameters assessed include horizontal and vertical distances (head), volume, and the total storage capacity of each reservoir, measured in GWh. By analyzing these factors, the tool determines the suitability of various lakes and dams for hydroelectric power generation, and other uses based on the horizontal and vertical threshold distances. Its robust assessment framework integrates these metrics to comprehensively evaluate each site's potential. The tool's friendly interface and advanced data visualization features make the findings easy to interpret, facilitating optimal resource utilization and informed decision-making for state authorities. Hence, this tool represents a meaningful advancement in managing Michigan's water resources sustainably, promoting environmentally friendly practices, and supporting economic development.

eess.SY↗

Pre-Trained Large Language Model Based Remaining Useful Life Transfer Prediction of Bearing

Accurately predicting the remaining useful life (RUL) of rotating machinery, such as bearings, is essential for ensuring equipment reliability and minimizing unexpected industrial failures. Traditional data-driven deep learning methods face challenges in practical settings due to inconsistent training and testing data distributions and limited generalization for long-term predictions.

eess.SY↗

Deep Learning-Based Electricity Price Forecast for Virtual Bidding in Wholesale Electricity Market

Virtual bidding plays an important role in two-settlement electric power markets, as it can reduce discrepancies between day-ahead and real-time markets. Renewable energy penetration increases volatility in electricity prices, making accurate forecasting critical for virtual bidders, reducing uncertainty and maximizing profits. This study presents a Transformer-based deep learning model to forecast the price spread between real-time and day-ahead electricity prices in the ERCOT (Electric Reliability Council of Texas) market. The proposed model leverages various time-series features, including load forecasts, solar and wind generation forecasts, and temporal attributes. The model is trained under realistic constraints and validated using a walk-forward approach by updating the model every week. Based on the price spread prediction results, several trading strategies are proposed and the most effective strategy for maximizing cumulative profit under realistic market conditions is identified through backtesting. The results show that the strategy of trading only at the peak hour with a precision score of over 50% produces nearly consistent profit over the test period. The proposed method underscores the importance of an accurate electricity price forecasting model and introduces a new method of evaluating the price forecast model from a virtual bidder's perspective, providing valuable insights for future research.

cs.LG↗

Study on the Time Domain Precision Evolution Mechanism of CNC Machine Tool Feed Systems Based on Acceleration and Deceleration Capability Indicator

The escalating demand for high-speed and high-precision machining in machine tool feed system has brought to the forefront the challenge of its design method. Currently, existing methodologies struggle to ascertain compliance with dynamic performance requirements during the design phase, often resulting in either excessive or insufficient design. Therefore, there is an urgent need for research focused on feed system design methods that directly address time domain dynamic precision. The dynamic precision of the feed system is influenced by the motor, mechanical structure, motion processes, and control system. However, existing studies on the impact mechanisms of electromechanical matching on feed system precision often overlook the roles of control and motion processes. This paper innovatively proposes the need to consider the coupling effects among subsystems, directing the optimization design of CNC machine tool feed systems towards time domain dynamic precision. Furthermore, it introduces acceleration and deceleration capability as a key indicator of electromechanical matching. Following the decoupling of control system parameters, this study elucidates the influence mechanisms of electromechanical matching on the overall dynamic performance of the feed system under various motion processes. This research offers a novel design philosophy and theoretical foundation for the optimization of CNC machine tool feed systems.

eess.SY↗

Optimal balanced-norm error estimate of the LDG method for reaction-diffusion problems II: the two-dimensional case with layer-upwind flux

A singularly perturbed reaction-diffusion problem posed on the unit square in $\mathbb{R}^2$ is solved numerically by a local discontinuous Galerkin (LDG) finite element method. Typical solutions of this class of 2D problems exhibit boundary layers along the sides of the domain; these layers generally cause difficulties for numerical methods. Our LDG method handles the boundary layers by using a Shishkin mesh and also introducing the new concept of a ``layer-upwind flux" -- a discrete flux whose values are chosen on the fine mesh (which lies inside the boundary layers) in the direction where the layer weakens. On the coarse mesh, one can use a standard central flux. No penalty terms are needed with these fluxes, unlike many other variants of the LDG method. Our choice of discrete flux makes it feasible to derive an optimal-order error analysis in a balanced norm; this norm is stronger than the usual energy norm and is a more appropriate measure for errors in computed solutions for singularly perturbed reaction-diffusion problems. It will be proved that the LDG method is usually convergent of order $O((N^{-1}\ln N)^{k+1})$ in the balanced norm, where $N$ is the number of mesh intervals in each coordinate direction and tensor-product piecewise polynomials of degree~$k$ in each coordinate variable are used in the LDG method. This result is the first of its kind for the LDG method applied to this class of problem and is optimal for convergence on a Shishkin mesh. Its sharpness is confirmed by numerical experiments.

math.NA↗

MetaFollower: Adaptable Personalized Autonomous Car Following

Car-following (CF) modeling, a fundamental component in microscopic traffic simulation, has attracted increasing interest of researchers in the past decades. In this study, we propose an adaptable personalized car-following framework -MetaFollower, by leveraging the power of meta-learning. Specifically, we first utilize Model-Agnostic Meta-Learning (MAML) to extract common driving knowledge from various CF events. Afterward, the pre-trained model can be fine-tuned on new drivers with only a few CF trajectories to achieve personalized CF adaptation. We additionally combine Long Short-Term Memory (LSTM) and Intelligent Driver Model (IDM) to reflect temporal heterogeneity with high interpretability. Unlike conventional adaptive cruise control (ACC) systems that rely on predefined settings and constant parameters without considering heterogeneous driving characteristics, MetaFollower can accurately capture and simulate the intricate dynamics of car-following behavior while considering the unique driving styles of individual drivers. We demonstrate the versatility and adaptability of MetaFollower by showcasing its ability to adapt to new drivers with limited training data quickly. To evaluate the performance of MetaFollower, we conduct rigorous experiments comparing it with both data-driven and physics-based models. The results reveal that our proposed framework outperforms baseline models in predicting car-following behavior with higher accuracy and safety. To the best of our knowledge, this is the first car-following model aiming to achieve fast adaptation by considering both driver and temporal heterogeneity based on meta-learning.

cs.LG↗

Video Frame Interpolation for Polarization via Swin-Transformer

Video Frame Interpolation (VFI) has been extensively explored and demonstrated, yet its application to polarization remains largely unexplored. Due to the selective transmission of light by polarized filters, longer exposure times are typically required to ensure sufficient light intensity, which consequently lower the temporal sample rates. Furthermore, because polarization reflected by objects varies with shooting perspective, focusing solely on estimating pixel displacement is insufficient to accurately reconstruct the intermediate polarization. To tackle these challenges, this study proposes a multi-stage and multi-scale network called Swin-VFI based on the Swin-Transformer and introduces a tailored loss function to facilitate the network's understanding of polarization changes. To ensure the practicality of our proposed method, this study evaluates its interpolated frames in Shape from Polarization (SfP) and Human Shape Reconstruction tasks, comparing them with other state-of-the-art methods such as CAIN, FLAVR, and VFIT. Experimental results demonstrate our approach's superior reconstruction accuracy across all tasks.

cs.CV↗

Research on material identification of mobile phones falling to the ground

The failure mode of the phone falling has a lot to do with the ground material. At present, the research on ground material and mobile phone damage is generally carried out through experiments, which is extremely costly. This paper presents a method to identify the material of mobile phones falling on the ground. The method determines the material of the mobile phone falling to the ground according to the data of the mobile phone accelerometer and can obtain the ground material of the mobile phone falling through a large number of user data. By analyzing the physical process of mobile phone falling, the accelerometer data interval which can reflect the characteristics of falling is reasonably intercepted. And the data features that can reflect the collision are extracted. Finally, based on the fully connected neural network, the method of determining the material of mobile phones falling on the ground is developed. The experimental results show that the method has a high identification rate, and the average identification rate for different ground materials is 96.75%. Instead of relying on auxiliary devices, the identification process only relies on the phone's built-in acceleration sensor. This paper fills the gap in the field of mobile phone falling ground material identification. It has a great contribution to the collection of user drop data, the analysis of the drop process, and the improvement of mobile phone design defects.

eess.SY↗

A review of dynamics design methods for high-speed and high-precision CNC machine tool feed systems

With the development of CNC machine tools toward high speed and high precision, the traditional static design methods can hardly meet the demand. Hence, in this paper, the dynamics matching design methods of existing CNC machine tool feed systems were investigated and analyzed. Further, sub-system coupling mechanisms and optimization design studies were carried out for each sub-system. First, the required kinematic indexes must be achieved when designing the feed system dynamics of high-speed, high-precision CNC machine tools. Second, the CNC machine tool feed systems generally have four sub-systems: motion process, control system, motor, and mechanical structure. The coupling effect between the sub-systems should also be considered in the design. Based on the dynamics design, each sub-system should be optimized to maximize the system dynamic performance with minimum resource allocation. Finally, based on the review, future research directions within the field were detected.

eess.SY↗

Deep Learning-Based Weather-Related Power Outage Prediction with Socio-Economic and Power Infrastructure Data

This paper presents a deep learning-based approach for hourly power outage probability prediction within census tracts encompassing a utility company's service territory. Two distinct deep learning models, conditional Multi-Layer Perceptron (MLP) and unconditional MLP, were developed to forecast power outage probabilities, leveraging a rich array of input features gathered from publicly available sources including weather data, weather station locations, power infrastructure maps, socio-economic and demographic statistics, and power outage records. Given a one-hour-ahead weather forecast, the models predict the power outage probability for each census tract, taking into account both the weather prediction and the location's characteristics. The deep learning models employed different loss functions to optimize prediction performance. Our experimental results underscore the significance of socio-economic factors in enhancing the accuracy of power outage predictions at the census tract level.

cs.LG↗

Active Learning for NLP with Large Language Models

Human annotation of training samples is expensive, laborious, and sometimes challenging, especially for Natural Language Processing (NLP) tasks. To reduce the labeling cost and enhance the sample efficiency, Active Learning (AL) technique can be used to label as few samples as possible to reach a reasonable or similar results. To reduce even more costs and with the significant advances of Large Language Models (LLMs), LLMs can be a good candidate to annotate samples. This work investigates the accuracy and cost of using LLMs (GPT-3.5 and GPT-4) to label samples on 3 different datasets. A consistency-based strategy is proposed to select samples that are potentially incorrectly labeled so that human annotations can be used for those samples in AL settings, and we call it mixed annotation strategy. Then we test performance of AL under two different settings: (1) using human annotations only; (2) using the proposed mixed annotation strategy. The accuracy of AL models under 3 AL query strategies are reported on 3 text classification datasets, i.e., AG's News, TREC-6, and Rotten Tomatoes. On AG's News and Rotten Tomatoes, the models trained with the mixed annotation strategy achieves similar or better results compared to that with human annotations. The method reveals great potentials of LLMs as annotators in terms of accuracy and cost efficiency in active learning settings.

cs.CL↗

AccidentGPT: Accident Analysis and Prevention from V2X Environmental Perception with Multi-modal Large Model

Traffic accidents, being a significant contributor to both human casualties and property damage, have long been a focal point of research for many scholars in the field of traffic safety. However, previous studies, whether focusing on static environmental assessments or dynamic driving analyses, as well as pre-accident predictions or post-accident rule analyses, have typically been conducted in isolation. There has been a lack of an effective framework for developing a comprehensive understanding and application of traffic safety. To address this gap, this paper introduces AccidentGPT, a comprehensive accident analysis and prevention multi-modal large model. AccidentGPT establishes a multi-modal information interaction framework grounded in multi-sensor perception, thereby enabling a holistic approach to accident analysis and prevention in the field of traffic safety. Specifically, our capabilities can be categorized as follows: for autonomous driving vehicles, we provide comprehensive environmental perception and understanding to control the vehicle and avoid collisions. For human-driven vehicles, we offer proactive long-range safety warnings and blind-spot alerts while also providing safety driving recommendations and behavioral norms through human-machine dialogue and interaction. Additionally, for traffic police and management agencies, our framework supports intelligent and real-time analysis of traffic safety, encompassing pedestrian, vehicles, roads, and the environment through collaborative perception from multiple vehicles and road testing devices. The system is also capable of providing a thorough analysis of accident causes and liability after vehicle collisions. Our framework stands as the first large model to integrate comprehensive scene understanding into traffic safety studies. Project page: https://accidentgpt.github.io

cs.CE↗