Artificial Intelligence and Robotics Commons^™

Learning Orientation Field For Osm-Guided Autonomous Navigation, Yuming Huang, Wei Gao, Zhiyuan Zhang, Maani Ghaffari, Dezhen Song, Cheng-Zhong Xu, Hui Kong

Research Collection School Of Computing and Information Systems

OpenStreetMap (OSM) has gained popularity recently in autonomous navigation due to its public accessibility, lower maintenance costs, and broader geographical coverage. However, existing methods often struggle with noisy OSM data and incomplete sensor observations, leading to inaccuracies in trajectory planning. These challenges are particularly evident in complex driving scenarios, such as at intersections or facing occlusions. To address these challenges, we propose a robust and explainable two-stage framework to learn an Orientation Field (OrField) for robot navigation by integrating LiDAR scans and OSM routes. In the first stage, we introduce a novel representation, OrField, which can provide orientations for each …

Recurrent Autoregressive Linear Model For Next-Basket Recommendation, Tereza Zmeskalova, Antoine Ledent, Martin Spisak, Pavel Kordik, Rodrigo Alves

Research Collection School Of Computing and Information Systems

Next-basket recommendation aims to predict the (sets of) items that a user is most likely to purchase during their next visit, capturing both short-term sequential patterns and long-term user preferences. However, effectively modeling these dynamics remains a challenge for traditional methods, which often struggle with interpretability and computational efficiency, particularly when dealing with intricate temporal dependencies and inter-item relationships. In this paper, we propose ReALM, a Recurrent Autoregressive Linear Model that explicitly captures temporal item-to-item dependencies across multiple time steps. By leveraging a recurrent loss function and a closed-form optimization solution, our approach offers both interpretability and scalability while maintaining …

Stable And Fair Cost Allocation In Platform-Enabled Lcl Consolidation, Pang Jin Tan, Shih-Fen Cheng

Research Collection School Of Computing and Information Systems

Many logistics platforms enable collaboration between agents to reduce costs, but determining fair pricing remains challenging when agents have pre-existing partnerships. This paper introduces a cooperative game theory framework to model platform-mediated collaboration, modeling the platform as an additional player. We present a novel characteristic function that distinguishes between partial collaborations (existing relationships) and full collaborations (platform-enabled). Using Shapley value, we derive fair cost allocations and platform charges that reflect each participant's contribution. We address stability concerns through an optimization model that minimizes platform subsidies while preventing profitable deviations. The framework is demonstrated through an application in freight forwarding for …

Preference-Based Deep Reinforcement Learning For Historical Route Estimation, Boshen Pan, Yaoxin Wu, Zhiguang Cao, Yaqing Hou, Guangyu Zou, Qiang Zhang

Research Collection School Of Computing and Information Systems

Recent Deep Reinforcement Learning (DRL) techniques have advanced solutions to Vehicle Routing Problems (VRPs). However, many of these methods focus exclusively on optimizing distance-oriented objectives (i.e., minimizing route length), often overlooking the implicit drivers' preferences for routes. These preferences, which are crucial in practice, are challenging to model using traditional DRL approaches. To address this gap, we propose a preference-based DRL method characterized by its reward design and optimization objective, which is specialized to learn historical route preferences. Our experiments demonstrate that the method aligns generated solutions more closely with human preferences. Moreover, it exhibits strong generalization performance across a …

Lighttransfer: Your Long-Context Llm Is Secretly A Hybrid Model With Effortless Adaptation, Xuan Zhang, Fengzhuo Zhang, Cunxiao Du, Chao Du, Tianyu Pang, Wei Gao, Min Lin

Research Collection School Of Computing and Information Systems

Scaling language models to handle longer contexts introduces substantial memory challenges due to the growing cost of key-value (KV) caches. Motivated by the efficiency gains of hybrid models and the broad availability of pretrained large transformer backbones, we explore transitioning transformer models into hybrid architectures for a more efficient generation. In this work, we propose LightTransfer, a lightweight method that transforms models such as LLaMA into hybrid variants. Our approach identifies lazy layers -- those focusing on recent or initial tokens -- and replaces their full attention with streaming attention. This transformation can be performed without any training for long-context …

Towards Multimodal Emotional Support Conversation Systems, Yuqi Chu, Lizi Liao, Zhiyuan Zhou, Chong-Wah Ngo, Richang Hong

Research Collection School Of Computing and Information Systems

The integration of conversational artificial intelligence (AI) into mental health care promises a new horizon for therapist-client interactions, aiming to closely emulate the depth and nuance of human conversations. Despite the potential, the current landscape of conversational AI is markedly limited by its reliance on single-modal data, constraining the systems’ ability to empathize and provide effective emotional support. This limitation stems from a paucity of resources that encapsulate the multimodal nature of human communication essential for therapeutic counseling. To address this gap, we introduce the Multimodal Emotional Support Conversation (MESC) dataset, a first-of-its-kind resource enriched with comprehensive annotations across text, …

Guiding Multiple Remote Users In Physical Tasks With Language-Driven Robotic Telepresence, Ruyi Li, Jingfei Guo, Xinyi Zhang, Xuji Zhang, Zeqing Li, Jiannan Li, Jiangtao Gong

Research Collection School Of Computing and Information Systems

Remote assistance through robotic telepresence could involve both control and memory challenges, particularly in one expert to multiple workers situation. In this work, we proposed a novelty language-driven interface to facilitate remote collaboration through telepresence robots. Through operations and maintenance expert interviews and a scenario simulation study, we identified key pain points in executing one-expert-multiple-workers remote guidance using the telepresence robot and proposed two design goals, which together consist of five sub-design goals with corresponding features. These features were integrated into a standard telepresence robot, resulting in the development of a Collaborative LLM-based Embodied Assistant Robot, named CLEAR Robot. A …

Implementing Slack-Free Custom Penalty Function For Qubo On Gate-Based Quantum Computers, Xin Wei Lee, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

Solving NP-hard constrained combinatorial optimization problems using quantum algorithms remains a challenging yet promising avenue toward quantum advantage. Variational Quantum Algorithms (VQAs), such as the Variational Quantum Eigensolver (VQE), typically require constrained problems to be reformulated as unconstrained ones using penalty methods. A common approach introduces slack variables and quadratic penalties in the QUBO formulation to handle inequality constraints. However, this leads to increased qubit requirements and often distorts the optimization landscape, making it harder to find high-quality feasible solutions. To address these issues, we explore a slack-free formulation that directly encodes inequality constraints using custom penalty functions, specifically the …

Conv4rec: A 1‑By‑1 Convolutional Autoencoder For User Profiling Through Joint Analysis Of Implicit And Explicit Feedbacks, Antoine Ledent, Petr Kasalický, Rodrigo Alves, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

We introduce a new convolutional autoencoder architecture for user modeling and recommendation tasks with several improvements over the state of the art. First, our model has the flexibility to learn a set of associations and combinations between different interaction types in a way that carries over to each user and item. Second, our model is able to learn jointly from both the explicit ratings and the implicit information in the sampling pattern (which we refer to as ”implicit feedback”). It can also make separate predictions for the probability of consuming content and the likelihood of granting it a high rating …

Advancing U.S. Competitiveness In Agentic Gen Ai: A Strategic Framework For Interoperability And Governance, Satyadhar Joshi

Harrisburg University Other Works

Abstract : The rapid evolution of artificial intelligence has given rise to agentic AI systems—autonomous entities capable of perceiving their environment, making decisions, and executing actions with minimal human intervention. This work provides a systematic analysis of agentic AI frameworks, governance models, and implementation strategies. Drawing on a comprehensive review of the literature, we examine the current state of agentic AI technologies, highlight key challenges in governance, security, and ethical oversight, and compare architectural frameworks for responsible deployment. Our results, illustrated through detailed framework comparisons and governance analyses, demonstrate that while agentic AI holds transformative potential across multiple sectors, notable …

Robust Ai Solutions For Financial Markets Through Generative Modeling, Dynamic Graph Learning, And Reinforcement-Based Portfolio Optimization, Jingyi Gu

Dissertations

Financial markets are inherently uncertain and dynamic, driven by complex factors such as macroeconomic signals, investor sentiment, and evolving inter-asset relationships. While machine learning has advanced financial modeling, existing approaches often fall short in addressing the real-world intricacies of finance. This dissertation confronts two critical challenges, human-driven stochasticity and risk-intensive decision-making under real-world trading constraints, while seizing a pivotal opportunity, the structural dynamics of evolving financial systems. These elements are foundational to advancing robust and practical financial intelligence.

To this end, this dissertation develops a unified framework for robust financial modeling and decision-making. The framework is architected as a progressive, …

Optimizing Hip And Knee Assistance For Walking And Sit-To-Stand Transitions: An Intrinsic Muscle Mechanics Based Predictive Approach, Neethan Ratnakumar

Dissertations

As the global population ages, the demand for wearable assistive technologies continues to rise, driven by their potential to enhance mobility and independence in older adults. Effectively designed controllers for lower-limb exoskeletons to assist sit-to-stand (STS) and walking are crucial for delivering efficient, safe, and comfortable assistance during daily activities. Traditionally, controller optimization involves biomechanical modeling and user-specific customization. Musculoskeletal simulations play a central role in this process by providing insights into human-exoskeleton interaction dynamics, thereby informing and refining control strategies.

This work presents a simulation-driven approach for developing exoskeleton controllers for walking and STS using two distinct methods: optimal …

Sugar: A Sequence Unfolding Based Transformer Model For Group Activity Recognition, Yash U. Gondkar

Graduate Masters Theses

Large Language Models have improved significantly in the past couple of years due to the adoption of transformers. However, transformers still find it challenging to process videos due to limited context size caused by their quadratic computing cost. Therefore, we studied a booming field in machine learning which powers applications like social scene analysis and video surveillance systems called Group Activity Recognition (GAR). We found that recent models were able to achieve more than 90% accuracy on popular datasets like the Volleyball dataset, however, it turned out that even they relied on transformers.

Therefore, in this work, we developed a …

Can Artificial Intelligence Models Provide Reliable Medical Counselling To Fertility Patients?, Idan Alcalay, Ariel Weissman, Hadas Ganer Herman, Avi Tsafrir, Matan Friedman, Eran Weiner, Raoul Orvieto, Nikolaos P. Polyzos, Michael H. Dahan, Alex Polyakov, Robert Fischer, Sandro C. Esteves, Baris Ata, Jason M. Franasiak, Yossi Mizrachi

Department of Obstetrics and Gynecology Faculty Papers

RESEARCH QUESTION: Can generative artificial intelligence (AI) models provide reliable counselling to fertility patients regarding real-world clinical questions?

DESIGN: In this cross-sectional study, 12 clinical questions were developed to reflect common, real-life dilemmas encountered during fertility workup and treatment. Responses to each question were generated by two experienced fertility specialists, and two AI models - ChatGPT and Gemini. Eight leading internationally recognized fertility experts, blinded to the source of each reply, independently rated all the responses on a scale from 1 (strongly disagree) to 10 (strongly agree). Ratings were compared across all four repliers using non-parametric statistical tests.

RESULTS: The …

A Dual-Model Machine Learning Framework For Predictive Maintenance Of Industrial Digital Press Components, Richmond Darko, Emmanuel Adabor

African Conference on Information Systems and Technology

This study presents a novel dual-model predictive maintenance framework designed to improve maintenance scheduling for components in industrial digital presses. The framework integrates two complementary approaches: a Threshold-Based Maintenance Approach (TBMA) for components operating within acceptable usage limits, and an Overdue Severity-Based Maintenance Approach (OSBMA) for those that have exceeded their expected lifespans or show signs of critical degradation. This study uses real-world operational data from a Konica Minolta C6000 press. It applies advanced machine learning models, including Gradient Boosting Machines and Random Forest for classification, and Generalized Additive Models (GAM) for Remaining Useful Life (RUL) prediction. The goal is …

Feasibility Evaluation Of Secure Offline Large Language Models With Retrieval-Augmented Generation For Cpu-Only Inference, Erick Tyndall, Torrey J. Wagner, Colleen Gayheart, Alexandre Some, Brent T. Langhals

Faculty Publications

Recent advances in large language models and retrieval-augmented generation, a method that enhances language models by integrating retrieved external documents, have created opportunities to deploy AI in secure, offline environments. This study explores the feasibility of using locally hosted, open-weight large language models with integrated retrieval-augmented generation capabilities on CPU-only hardware for tasks such as question answering and summarization. The evaluation reflects typical constraints in environments like government offices, where internet access and GPU acceleration may be restricted. Four models were tested using LocalGPT, a privacy-focused retrieval-augmented generation framework, on two consumer-grade systems: a laptop and a workstation. A technical …

Machine Learning And Crime Prevention, Emily Lizewski

Student Theses

Predictive policing uses machine learning to analyze crime patterns and help law enforcement better efficient use their resources. These tools can improve accuracy by highlighting complex trends in large sets of data. While this technology has its advantages, it also raises important ethical and social questions. Within this paper we looks at how predictive policing works, focusing on the machine learning models often used such as decision trees, random forests, gradient boosting, and models that factor in both time and location. It also explores how these tools might unintentionally reinforce biases already present in historical crime data. In reviewing the …

Ai Is Not The New Dei: Academia’S Addiction To The Next Big Thing, Essraa Nawar

Library Articles and Research

"Every August, as campuses come back to life across the country and the world, I notice the same rhythm: new policies announced, committees formed, webinars scheduled, and fall conferences themed around the latest 'big thing.'

This fall? No surprise. The wave is artificial intelligence.

AI task forces are meeting weekly. Universities are drafting 'responsible AI' policies. New centers and certificates are being launched. Syllabi are being rewritten. Symposia and faculty retreats promise that AI will 'redefine the future of education.'

It is bold. It is ambitious. But it is also deeply familiar."

Intelligent Motion Tracking: A Low-Cost Surveillance Framework Using Soc Devices And Sensor Fusion, Aung Myat Khaung, Nicholas Michael Stiffler

Research from the Berry Summer Thesis Institute, 2025

This thesis presents the design and implementation of a lightweight surveillance system capable of realtime motion detection, object tracking, and behavioral history reconstruction in controlled environments. The system uses System-on-Chip devices such as Raspberry Pi boards equipped with NOIR cameras, monocular cameras, and break-beam sensors that work together to detect and track single or multiple moving objects like colored balls. The prototype is validated in structured settings with the goal of eventual deployment in more dynamic environments, addressing the challenge of reliably tracking visually similar objects with minimal distinguishing features. The architecture integrates computer vision with sensor fusion by combining …

Performance Analysis Of Computational Methods For Predicting Protein Function In Rare Diseases, Aichetou Mohamed Sidiya, Hanin Alzaher, Razan Almahdi, Tayeb Brahimi

Effat Undergraduate Research Journal

Protein function prediction is crucial for understanding the underlying mechanisms of rare diseases. With the increasing availability of computational methods including machine learning-based approaches, network-based methods, and sequence-based methods, predicting protein functions has become more accessible. However, it is not clear which of these methods performs better or how they compare to each other in terms of accuracy, efficiency, and scalability. In this study, we evaluate several computational methods for predicting protein functions in rare diseases using key performance indicators (KPIs). We analyze the strengths and weaknesses of each method and provide recommendations for researchers and clinicians interested in using …