Artificial Intelligence and Robotics Commons^™

Ai As Your Ally: The Effects Of Ai-Assisted Venting On Negative Affect And Perceived Social Support, Meilan Hu, Xavier Cheng Wee Chua, Shu Fen Diong, K. T. A. Sandeeshwara Kasturiratna, Nadyanna M. Majeed, Andree Hartanto

Research Collection School of Social Sciences

In recent years, artificial intelligence (AI) chatbots have made significant strides in generating human-like conversations. With AI's expanding capabilities in mimicking human interactions, its affordability and accessibility underscore the potential of AI chatbots to facilitate negative emotional disclosure or venting. The study's primary objective is to highlight the potential benefits of AI-assisted venting by comparing its effectiveness to venting through a traditional journaling platform in reducing negative affect and increasing perceived social support. We conducted a pre-registered within-subject experiment involving 150 participants who completed both traditional venting and AI-assisted venting conditions with counterbalancing and a wash-out period of 1-week between …

Proactive Conversational Ai: A Comprehensive Survey Of Advancements And Opportunities, Yang Deng, Lizi Liao, Wenqiang Lei, Grace Hui Yang, Wai Lam, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Dialogue systems are designed to offer human users social support or functional services through natural language interactions. Traditional conversation research has put significant emphasis on a system's response-ability, including its capacity to understand dialogue context and generate appropriate responses. However, the key element of proactive behavior-a crucial aspect of intelligent conversations-is often overlooked in these studies. Proactivity empowers conversational agents to lead conversations towards achieving pre-defined targets or fulfilling specific goals on the system side. Proactive dialogue systems are equipped with advanced techniques to handle complex tasks, requiring strategic and motivational interactions, thus representing a significant step towards artificial general …

Loco: Low-Bit Communication Adaptor For Large-Scale Model Training, Xingyu Xie, Zhijie Lin, Kim-Chuan Toh, Pan Zhou

Research Collection School Of Computing and Information Systems

To efficiently train large-scale models, low-bit gradient communication compresses full-precision gradients on local GPU nodes into low-precision ones for higher gradient synchronization efficiency among GPU nodes. However, it often degrades training quality due to compression information loss. To address this, we propose the Low-bit Communication Adaptor (LoCo), which compensates gradients on local GPU nodes before compression, ensuring efficient synchronization without compromising training quality. Specifically, LoCo designs a moving average of historical compensation errors to stably estimate concurrent compression error and then adopts it to compensate for the concurrent gradient compression, yielding a less lossless compression. This mechanism allows it to …

A Causality-Aware Paradigm For Evaluating Creativity Of Multimodal Large Language Models, Zhongzhan Huang, Shanshan Zhong, Pan Zhou, Shanghua Gao, Marink Zitnik, Liang Lin

Research Collection School Of Computing and Information Systems

Recently, numerous benchmarks have been developed to evaluate the logical reasoning abilities of large language models (LLMs). However, assessing the equally important creative capabilities of LLMs is challenging due to the subjective, diverse, and data-scarce nature of creativity, especially in multimodal scenarios. In this paper, we consider the comprehensive pipeline for evaluating the creativity of multimodal LLMs, with a focus on suitable evaluation platforms and methodologies. First, we find the Oogiri game—a creativity-driven task requiring humor, associative thinking, and the ability to produce unexpected responses to text, images, or both. This game aligns well with the input-output structure of modern …

Towards Resource-Efficient Reactive And Proactive Auto-Scaling For Microservice Architectures, Hussain Ahmad, Christoph Treude, Markus Wagner, Claudia Szabo

Research Collection School Of Computing and Information Systems

Microservice architectures have become increasingly popular in both academia and industry, providing enhanced agility, elasticity, and maintainability in software development and deployment. To simplify scaling operations in microservice architectures, container orchestration platforms such as Kubernetes feature Horizontal Pod Auto-scalers (HPAs) designed to adjust the resources of microservices to accommodate fluctuating workloads. However, existing HPAs are not suitable for resource-constrained environments, as they make scaling decisions based on the individual resource capacities of microservices, leading to service unavailability, resource mismanagement, and financial losses. Furthermore, the inherent delay in initializing and terminating microservice pods hinders HPAs from timely responding to workload fluctuations, …

Human‑Ai And Human‑Robot Collaboration In The Age Of Generative Ai, Agentic Ai, And Artificial General Intelligence: Opportunities And Challenges, Keng Siau

Research Collection School Of Computing and Information Systems

The advancement of Artificial Intelligence (AI) has been exponential, especially in the past few years. Most, if not all, of the AI systems we encounter and are exposed to at this point are Artificial Narrow Intelligence (ANI). ANI specializes in one area and solves problems in one area. Generative AI (GenAI) and Agentic AI (i.e., independent AI agent), at the current stage of development, are regarded as ANI. The race is currently on to develop Artificial General Intelligence (AGI). AGI refers to AI systems as smart as humans across a wide range of cognitive tasks. Recently, OpenAI’s o3 system received …

Negotiating With Gpt-4: Digital Doormat Or Skilful Counterpart?, Dorcas Quek Anderson

Research Collection Yong Pung How School Of Law

Large language models (LLMs) such as GPT-4 have been creatively harnessed in the conflict resolution arena as dialogue agents interacting with humans within negotiations, due to their capacity for in-context learning and giving human-like responses. In light of the burgeoning use of LLMs in conflict resolution training, a pilot study was conducted to ascertain the desirability of using dialogue agents built on GPT-4 in conducting simulations for students learning negotiation skills. This article discusses insights gained from the study on the reliability of LLM agents in following prompts for negotiation simulations; notable negotiation behaviour of the LLM agent; the degree …

Towards The Next Generation Of Geospatial Artificial Intelligence, Gengchen Mai, Yiqun Xie, Xiaowei Jia, Ni Lao, Jinmeng Rao, Qing Zhu, Zeping Liu, Yao-Yi Chiang, Jiao, Junfeng

Research Collection College of Integrative Studies

Geospatial Artificial Intelligence (GeoAI), as the integration of geospatial studies and AI, has become one of the fastest-developing research directions in spatial data science and geography. This rapid change in the field calls for a deeper understanding of the recent developments and envision where the field is going in the near future. In this work, we provide a quantitative analysis of the GeoAI literature from the spatial, temporal, and semantic aspects. We briefly discuss the history of AI and GeoAI by highlighting some pioneering work. Then we discuss the current landscape of GeoAI by selecting five representative subdomains including remote …

Heartdj - Music Recommendation And Generation Through Biofeedback From Heart Rate Variability, Egemen Şahin

Dartmouth College Master’s Theses

This study investigates the integration of real-time physiological data with AI-generated music to enhance emotional well-being, stress regulation, and focus, using Heart Rate Variability (HRV) as a biomarker of autonomic function. Conducted in two phases—Stable Audio Open (SAO) and Suno (SUNO)—the research evaluates biofeedback-driven music interventions across varying daily music-listening habits.

In the SAO phase, short AI-generated instrumental tracks were compared with Spotify recommendations and guided meditation. Modest HRV improvements were observed in biofeedback conditions, but participants noted emotional limitations, citing short track lengths and abrupt transitions.

The SUNO phase addressed these limitations with longer, more complex AI-generated compositions combined …

A Robust Framework For Graph Construction In Vision Graph Neural Networks, Ismael Elsharkawi

Theses and Dissertations

In Computer Vision, the method of representing an image has a profound effect on the performance of a model. Traditionally speaking, an image is treated as a grid of pixels and can be processed via Convolution Neural Net- works (CNN). An image can also be treated as a sequence of patches. Vision Transformers and MLP-Mixers (Multi-Layer Perceptron Mixers) are two types of models that process an image as a sequence. A more generic representation than grids and sequences would be graphs. That is why Vision Graph Neural Network (ViG) construct a graph for an image and process the image as …

Deep Learning-Based Auto-Segmentation For Liver Yttrium-90 Selective Internal Radiation Therapy, Jun Li, Wookjin Choi, Rani Anne

Department of Radiation Oncology Faculty Papers

The aim was to evaluate a deep learning-based auto-segmentation method for liver delineation in Y-90 selective internal radiation therapy (SIRT). A deep learning (DL)-based liver segmentation model using the U-Net3D architecture was built. Auto-segmentation of the liver was tested in CT images of SIRT patients. DL auto-segmented liver contours were evaluated against physician manually-delineated contours. Dice similarity coefficient (DSC) and mean distance to agreement (MDA) were calculated. The DL-model-generated contours were compared with the contours generated using an Atlas-based method. Ratio of volume (RV, the ratio of DL-model auto-segmented liver volume to manually-delineated liver volume), and ratio of activity (RA, …

Playing The Digital Dialectic Game: Writing Pedagogy With Generative Ai, Rebekah Shultz Colby

University Writing Program: Faculty Scholarship

This article explores teaching writing with generative AI as critical play where students and teachers engage in an ethically dialectical and aleatory game with generative AI. I qualitatively surveyed 24 writing teachers about how they teach writing with generative AI as well as its advantages and disadvantages. I discovered that teachers used generative AI to teach about the ethics of generative AI's design and rhetorical use to avoid plagiarism. Teachers also critically played with generative AI to teach the writing process of invention, drafting, revision, and editing. Specifically, the critical, dialectical interplay of human and machine invents in aleatory and …

Unveiling The Potential Of Generative Artificial Intelligence: A Multidimensional Journey Into The Future, Keng Boon Ooi, Alex Koohang, Eugene Cheng Xi Aw, Tat Huei Cham, Cihan Cobanoglu, Charles Dennis, Yogesh K. Dwivedi, Jun Jie Hew, Heather Linton Kelly, Laurie Hughes, Chieh Yu Lin, Anubhav Mishra, Ian Phau, Ramakrishnan Raman, Marianna Sigala, Yun Chia Tang, Lai Wan Wong, Garry Wei Han Tan

Research outputs 2022 to 2026

Purpose: The launch of ChatGPT has brought the large language model (LLM)-based generative artificial intelligence (GAI) into the spotlight, triggering the interests of various stakeholders to seize the possible opportunities implicated by it. Nevertheless, there are also challenges that the stakeholders should observe when they are considering the potential of GAI. Given this backdrop, this study presents the viewpoints gathered from various subject experts on six identified areas. Design/methodology/approach: Through an expert-based approach, this paper gathers the viewpoints of various subject experts on the identified areas of tourism and hospitality, marketing, retailing, service operations, manufacturing and healthcare. Findings: The subject …

Incorporating Visual Information Into Natural Language Processing, Maxwell Mbabilla Aladago

Dartmouth College Ph.D Dissertations

Natural language describes entities in the world, some real and some abstract. It is also common practice to complement human learning of natural language with visual cues. This is evident in the heavily graphical nature of children’s literature which underscores the importance of visual cues in language acquisition. Similarly, the notion of “visual learners” is well recognized, reflecting the understanding that visual signals such as illustrations, gestures, and depictions effectively supplement language. In machine learning, two primary paradigms have emerged for training systems involving natural language. The first paradigm encompasses setups where pre-training and downstream tasks are exclusively in natural …

The Year Of Ai: Raising Campus Awareness Through Art, Exhibits, And Community Engagement, Essraa Nawar

Library Articles and Research

This poster highlights the Leatherby Libraries’ leadership in advancing AI literacy through creative, inclusive, and interdisciplinary approaches. As part of Chapman University’s “Year of AI,” the library launched initiatives such as Beyond the Lens and AI: The Next Chapter, blending art, ethics, and education to inspire campus-wide engagement. Through collaboration with IS&T, Town & Gown, and academic departments, the library positioned itself as a hub for ethical dialogue and innovation. The poster shares replicable models for how libraries can foster AI awareness through community partnerships, exhibitions, and experiential learning.

Sequential Convex Programming Using Safe Flight Corridor For Trajectory Planning Of Uavs, Zhu Wang, Zhenpeng Zhang, Mengtong Zhang, Guangtong Xu

Journal of System Simulation

Abstract: To address the issues of sensitivity to initial values and weak convergence of sequential convex programming(SCP) based time-optimal trajectory planning for UAVs, a SCP method using safety flight corridor, denoted as SFC-SCP(safe flight corridor-sequential convex programming) is proposed. According to the obstacle avoidance path obtained from the front-end path planning, a safe flight corridor is constructed by forming a convex polygon safe flight area without obstacles for each trajectory point. The non-convex obstacle avoidance constraint is converted into linear inequality constraints to improve convergence ability. The rear-end SCP method is used to transform the nonlinear trajectory optimization problem under …

Task Reallocation Method For Unmanned Swarm Under Adversarial Conditions, Lun Zhang, Mei Yang, Tuo Zhao, Shuiku Zhang, Jian Huang

Journal of System Simulation

Abstract: Heterogeneous unmanned swarms have important potential applications in future wars. However, during the high-intensity confrontation in the battlefield, how to efficiently and quickly redistribute the tasks carried by the damaged agents so that the swarms could successfully complete the mission is a difficult problem that must be addressed in the combat application of unmanned swarms. This paper proposes a task reallocation method named improved CNP-HA (contract net protocol-Hungarian algorithm). Through the allocation mechanism and the bidding mechanism, the method realizes the task reallocation of damaged agents with lower communication cost and faster speed comparing with baseline methods. In the …

Moving Target Velocity Measurement Method Based On Multi-View Observation Optimization Of Uav Image, Yuxin Wu, Zhilong Zhang, Aoxu Liu, Jiangwei Zou, Chuwei Li

Journal of System Simulation

Abstract: Measuring the position and velocity of moving targets is an important requirement for drone video analysis. In this paper, a moving target localization and velocity estimation algorithm based on least square optimization of UAV multi-view observation images is proposed: the video and corresponding pose parameters obtained by the airborne optoelectronic system are used to establish a line-of-sight model at multiple observation times, it is unified to the WGS-84 coordinate system by coordinate transformation, the position and velocity of the moving target are estimated based on the least squares algorithm. This algorithm does not require laser ranging information between the …

A Visual Servo Precision Assembly Method For Riveting Parts Based On Adaptive Extended Kalman Filtering, Zonggang Li, Yanbo Li, Jianjun Jiao, Yajiang Du

Journal of System Simulation

Abstract: Aiming at the problems of multiple peg-in-hole riveting parts in industrial production due to the large number of rivets, small gap between rivets and rivet holes, and irregular rivet distribution, resulting in complex assembly process constraints, high assembly accuracy requirements, and difficulty in realizing intelligent riveting process to improve assembly efficiency, a visual servo accurate assembly method of riveting parts based on adaptive extended Kalman filter is proposed. In order to realize the high-precision positioning of riveted parts assembly, on the basis of the traditional extended Kalman filtering, an adaptive noise estimator is introduced to eliminate the influence of …

Research And Realization Of Immersive Skeleton Simulation System, Zining Wang, Shijiang Luo, Weiya Chen, Hanbin Luo

Journal of System Simulation

Abstract: Skeleton, as one of the sliding sports in Winter Olympic Games, has the characteristics of high speed, complexity and danger. In order to reduce the risk of accidents during sliding, a series of immersive skeleton simulation system is constructed utilizing virtual reality. Based on the point cloud data obtained by laser scanning, the existing track is modeled to build a virtual track stadium and skeleton sliding model in Unreal Engine 4. The data collected by motion capture devices is employed to estimate the centroid of the person and enable glide control input. The simulated skeleton posture is captured and …

Global Selection And Local Differentiation Fusion For Vehicle Re-Identification, Shengjun Xu, Mengqian Zhang, Bohan Zhan, Guanghui Liu, Yuebo Meng

Journal of System Simulation

Abstract: To address the interference issues of different perspectives, complex backgrounds, and lighting intensity in vehicle re-identification caused by cross lens multi view differences, a vehicle reidentification network integrating global selection and local differentiation is proposed. Based on Resnet50 backbone network, a three-branch complementary network integrating global and local features is designed. The global branch is used to learn overall appearance information of the vehicle, while the local branch captures differential details of the vehicle. Based on attention mechanism, a context feature selection module (CFSM) is proposed to effectively separate vehicle information from complex background information, and a detail feature …

Vehicle Routing Problem With Drones Considering Zoned Distribution Of Epidemic Prevention Materials, Huawei Ma, Boying Yan

Journal of System Simulation

Abstract: To address the shortcomings of current contactless delivery methods in the collaborative distribution of epidemic prevention supplies, we introduce a specialized model called the vehicle routing problem with drones considering zoned distribution (VRPD-ZD). In order to solve the problem, a linear programming model is established with the shortest delivery time as the optimization objective, and a two-stage heuristic algorithm is proposed. The initial solution is generated by greedy algorithm in the first stage. In the second stage, we develop a Tabu search algorithm with genetic algorithm (TSGA) hybrid. This enhanced algorithm integrates a taboo list and employs advanced chromosome …

Research On Modeling And Simulation Of Collective Mechanical Props Performance Behavior, Lian He, Kexiang Huang, Dapeng Yan, Ruida Tang, Gangyi Ding

Journal of System Simulation

Abstract: In stage performances, the increasing number of mechanical props poses significant challenges to their control and design. Each creative modification requires a complete rehearsal, resulting in low efficiency and sensitivity to creative changes. To address these issues, a model for the collective performance behavior of mechanical props is proposed. It utilizes centroid growth and 3D linear interpolation to generate spatial states and optimizes them in the temporal dimension using gradient descent. Through the construction of 3D simulation experiments, the planning and optimization of collective mechanical prop performance behavior in the model are analyzed. Similarity evaluation is used to compare …

Novel Multi-Gait Strategy For Stable And Efficient Quadruped Robot Locomotion, Daoxun Zhang, Xieyuanli Chen, Zhengyu Zhong, Ming Xu, Zhiqiang Zheng, Huimin Lu

Journal of System Simulation

Abstract: Inspired by the natural gait transition mechanism of quadruped animals, a multi-gait motion strategy is proposed to realize the stable and efficient motion of quadruped robots on different terrains in response to the trade-off between motion energy efficiency and motion stability. The gait is defined based on the duty cycle parameters and phase bias to form the switching basis. Secondly, the affine transformation of gait parameters and the finite state machine are introduced to establish the switching sequence, which realizes the timely gait switching. The speed-gait mapping is designed based on the cost of transport (CoT) and the stability …

Design Of Robust Behavior Tree Control Architecture For Agents In Dynamic Task Environment, Qiwei Wang, Qi Zhang, Shuo Yang, Yong Peng

Journal of System Simulation

Abstract: In recent years, the environment in which agents perform tasks has become more open and dynamic, which puts forward higher requirements for the robustness of task planning and behavior scheduling of agents. As a classic behavior control architecture, behavior tree has the characteristics of modularity, behavior parameterization, and structure of both plan representation and reaction, which can effectively support the behavior representation, decision making and scheduling of agents. Based on the hybrid behavior strategy , this paper proposes a robust behavior tree control architecture for dynamic task environment to realize the prudent decision-making and reactive control of agents. The …

Decision Modeling And Solution Based On Game Adversarial Complex Systems, Jiachen Jiang, Zhengxuan Jia, Zhao Xu, Tingyu Lin, Pengpeng Zhao, Yiming Ou

Journal of System Simulation

Abstract: In view of the complex situation of the current game which will be large-scale, high-intensity, not omniscient, and strong confrontation, and in response to the lack of flexibility and long iteration cycles in traditional game decision-making, the model of the unmanned complex game system is built according to the background of the unmanned red and blue game. Based on deep reinforcement learning technology, intelligent decision-making algorithms are studied in the background of unmanned red and blue games. With the help of deep neural networks and Bellman's optimal principle, the search of the huge solution space is more efficient, and …

Cooperative Control Method Of Mixed Traffic At Signalized Intersection, Qiushi Huang, Yanyang Wang, Changliang Wu, Junfu Huang, Shenggen Zhang, Haoxuan Luo

Journal of System Simulation

Abstract: A hierarchical decoupling cooperative control method for signal light mixed traffic platoon is designed with the goal of improving the traffic environment at signalized intersections. In the research of upper layer signal control, a calculation model for vehicle delay time at intersections is selected, with the goal of minimizing the average delay time of vehicles. A genetic algorithm based upper layer control strategy for intersection signal lights is proposed and verified; in the research of lower layer mixed platoon control, a "1+N" form is used to establish a dynamic model of the mixed platoon. A vehicle energy consumption model …

Driverless Vehicles Distribution Problem In Communities In Cooperation Of Storage Points, Xiaolong Diao

Journal of System Simulation

Abstract: With the development of smart communities, the distribution of driverless vehicles in communities has become a focus of government, operators and researchers. The joint cooperation of storage points in communities is designed to balance the the distribution of each storage point and avoid the high input cost of driverless vehicles, which means that driverless vehicles can travel between different storage points. The driverless vehicle distribution problem proposed in this paper includes the unloading subproblem and the driverless vehicle scheduling subproblem. For the unloading subproblem, the unloading scheme of vehicles at storage points is optimized with the aim of minimizing …

Multi-Uav Deployment And Collaborative Offloading For Large-Scale Iot Systems, Zhiqin Huang, Tianying Lu, Zheyi Chen

Journal of System Simulation

Abstract: In large-scale internet-of-things (IoT) systems, unmanned aerial vehicles (UAV) enabled mobile edge computing (MEC) can alleviate the performance constraints on end IoT devices. However, due to the uneven distribution of IoT devices and inefficient problem-solving, how to efficiently perform computation offloading in large-scale IoT systems is a major challenge. Existing solutions generally cannot fit into dynamic multi-UAV scenarios, causing inefficient resource utilization and excessive response delay. To address these important challenges, this paper proposes a novel multi-UAV deployment and collaborative offloading (MUCO) method for large-scale IoT systems. A UAV deployment scheme based on constrained K-Means clustering is designed to …

Uav Path Planning In Complex Environments And Its Improved Artificial Rabbits Optimization Algorithm, Anlin Yin, Zhuhong Zhang

Journal of System Simulation

Abstract: The work probes into the model design of reliable and effective UAV path planning in complex obstacle environments and its related optimization algorithm. In the model design, a weight coefficient method and cylindrical coordinate system-based single-objective path planning model is developed to solve the UAV's flight path, in which the distance, angle, height and threat cost are taken as performance indices and obstacles in the ground and spatial regions are regarded as constraints. In the algorithm design, the SPM chaotic mapping is used to improve the initial population distribution of the artificial rabbit optimization algorithm in view of the …