arXiv subjects

Hieu Bui

Publications and source records attributed to Hieu Bui.

5 recordsLinked to original sources

arXiv2026

Visual Prompt Guided Unified Pushing Policy

As one of the simplest non-prehensile manipulation skills, pushing has been widely studied as an effective means to rearrange objects. Existing approaches, however, typically rely on multi-step push plans composed of pre-defined pushing primitives with limited application scopes, which restrict their efficiency and versatility across different scenarios. In this work, we propose a unified pushing policy that incorporates a lightweight prompting mechanism into a flow matching policy to guide the generation of reactive, multimodal pushing actions. The visual prompt can be specified by a high-level planner, enabling the reuse of the pushing policy across a wide range of planning problems. Experimental results demonstrate that the proposed unified pushing policy not only outperforms existing baselines but also effectively serves as a low-level primitive within a VLM-guided planning framework to solve table-cleaning tasks efficiently.

cs.RO↗

arXiv2026

Can Vision-Language Models Understand Construction Workers? An Exploratory Study

As robotics become increasingly integrated into construction workflows, their ability to interpret and respond to human behavior will be essential for enabling safe and effective collaboration. Vision-Language Models (VLMs) have emerged as a promising tool for visual understanding tasks and offer the potential to recognize human behaviors without extensive domain-specific training. This capability makes them particularly appealing in the construction domain, where labeled data is scarce and monitoring worker actions and emotional states is critical for safety and productivity. In this study, we evaluate the performance of three leading VLMs, GPT-4o, Florence 2, and LLaVa-1.5, in detecting construction worker actions and emotions from static site images. Using a curated dataset of 1,000 images annotated across ten action and ten emotion categories, we assess each model's outputs through standardized inference pipelines and multiple evaluation metrics. GPT-4o consistently achieved the highest scores across both tasks, with an average F1-score of 0.756 and accuracy of 0.799 in action recognition, and an F1-score of 0.712 and accuracy of 0.773 in emotion recognition. Florence 2 performed moderately, with F1-scores of 0.497 for action and 0.414 for emotion, while LLaVa-1.5 showed the lowest overall performance, with F1-scores of 0.466 for action and 0.461 for emotion. Confusion matrix analyses revealed that all models struggled to distinguish semantically close categories, such as collaborating in teams versus communicating with supervisors. While the results indicate that general-purpose VLMs can offer a baseline capability for human behavior recognition in construction environments, further improvements, such as domain adaptation, temporal modeling, or multimodal sensing, may be needed for real-world reliability.

cs.CV↗

arXiv2024

Design of Targeted Community-Based Resource Allocation in the Presence of Vaccine Hesitancy via a Data-Driven Compartmental Stochastic Optimization Model

Vaccines have proven effective in mitigating the threat of severe infections and deaths during outbreaks of infectious diseases. However, vaccine hesitancy (VH) complicates disease spread prediction and healthcare resource assessment across regions and populations. We propose a modeling framework that integrates an epidemiological compartmental model that captures the spread of an infectious disease within a multi-stage stochastic program (MSP) that determines the allocation of critical resources under uncertainty. The proposed compartmental MSP model adaptively manages the allocation of resources to account for changes in population behavior toward vaccines (i.e., variability in VH), the unique patterns of disease spread, and the availability of healthcare resources over time and space. The compartmental MSP model allowed us to analyze the price of fairness in resource allocation. Using real COVID-19 vaccination and healthcare resource data from Arkansas, U.S. (January-May 2021), our findings include: (i) delaying the initial deployment of additional ventilators by one month could lead to an average increase in the expected number of deaths by 285.41/month, highlighting the importance of prompt action; (ii) each additional ventilator in the initial stockpile and in supply leads to a decrease in the expected number of deaths by 1.09/month and 0.962/month, respectively, emphasizing the importance of maintaining a large stockpile and scalable production response; (iii) the cost of ensuring equitable resource allocation varies over time and location, peaking during the peak of a disease outbreak and in densely populated areas. This study emphasizes the importance of flexible, informed public health decision-making and preparedness, providing a model for effective resource allocation in public health emergencies.

math.OC↗

arXiv2024

Evaluating the Impact of Vaccine Hesitancy on the Allocation of Vital Resources During COVID-19 Pandemic

The COVID-19 pandemic highlighted significant challenges in the allocation of vital healthcare resources. Existing epidemiological models, specifically compartmental models, aimed to predict the spread of the COVID-19 virus and its impact on the population, but they overlooked the influence of \ac{VH} on disease dynamics, including the expected number of hospitalizations and fatalities. We propose improvements to the \ac{SEIR} model for COVID-19 by incorporating the influence of vaccination, \ac{VH}, and resource availability on the disease dynamics. We collect publicly available data and perform data analysis to capture \ac{VH} dynamic changes over time and develop scenario paths for \ac{VH}. We simulate the proposed compartmental model for each \ac{VH} path to explain the impacts of public attitudes toward vaccination, the impacts of healthcare resources on patient outcomes, and the timing of vaccination rollout on the progression and severity of the epidemic. Our analysis demonstrates that reducing \ac{VH} improves health outcomes, reinforcing the importance of addressing \ac{VH} to curb the spread of infectious diseases. Our results show that adequate levels of critical healthcare resources are crucial for minimizing fatalities and also highlight the life-saving impact of timely and effective vaccination programs.

physics.soc-ph↗

arXiv2022

An Analysis of COVID-19 Vaccine Hesitancy in the U.S. at the County Level

Reluctance or refusal to get vaccinated, referred to as vaccine hesitancy (VH), has hindered the efforts of COVID-19 vaccination campaigns. It is important to understand what factors impact VH behavior. This information can help design public health interventions that could potentially increase vaccine uptake. We develop a random forest (RF) classification model that uses a wide variety of data to determine what factors affected VH at the county level during 2021. We consider static factors (such as gender, race, political affiliation, etc.) and dynamic factors (such as Google searches, social media postings, Stringency Index, etc.). Our model found political affiliation and the number of Google searches to be the most relevant factors in determining VH behavior. The RF classification model grouped counties of the U.S. into 5 clusters. VH is lowest in cluster 1 and highest in cluster 5. Most of the people who live in cluster 1 are democrat, are more internet-inquisitive (are more prone to seek information from multiple sources on the internet), have the longest life expectancy, have a college degree, have the highest income per capita, live in metropolitan areas. Most people who live in cluster 5 are republicans, are the least internet-inquisitive, have the shortest life expectancy, do not have a college degree, have the lowest income per capita, and live in non-metropolitan areas. Our model found that counties in cluster 1 were most responsive to vaccination-related policies and COVID-19 restrictions. These strategies did not have an impact on the VH of counties in cluster 5.

stat.AP↗