About

Maria Gini is a Professor in the Department of Computer Science & Engineering at the University of Minnesota. She joined the department in 1982 as an assistant professor and was later promoted to a full professor. Gini has served as the associate head of the department from 2005 to 2015. Her research focuses on decision making for autonomous agents across various application domains, including swarm robotics, distributed task allocation, exploration of unknown environments by robots, navigation in dense crowds, and conversational agents. She is a member of ACM, IEEE, and the IEEE Robotics Society, and has received numerous honors including being named a Morse-Alumni Distinguished Teaching Professor, a College of Science & Engineering Distinguished Professor, an IEEE Fellow, an ACM Fellow, and receiving the President’s Award for Outstanding Service. Gini has also been recognized for her contributions to mentoring and diversity in science and engineering.

Research topics

• Computer Science
• Artificial Intelligence
• Real-time computing
• Distributed computing
• Parallel computing
• Programming language
• Library science
• World Wide Web
• Operations research
• Statistics
• Algorithm
• Theoretical computer science
• Engineering
• Mathematics
• Human–computer interaction

Selected publications

• What Are You Looking Forward to? Deliberate Positivity as a Promising Strategy for Conversational Agents

  ACM Transactions on Interactive Intelligent Systems · 2025-03-27 · 2 citations

  articleOpen access

  Conversational agents (CAs) are one of the most promising technologies for helping older adults maintain independence longer by augmenting their support and social networks. Voice-based technology in particular is especially powerful in this regard due to its accessibility and ease of use. There is also a growing body of evidence supporting the potential use of such technology in mitigating common issues such as loneliness and isolation, particularly for independent older adults aging in place. One of the key challenges for smart technologies deployed in this context is the development and maintenance of long-term user engagement and adoption, which is often addressed by attempting to closely mimic human social interactions. However, the more human-like the system, the more glaring fault conditions become, and the more jarring they are for users. In this study we explore the effectiveness of an alternative conversational strategy meant to encourage users to engage in positive reflection and introspection. We detail the iterative design and implementation of a prototype CA developed to engage in social conversation with older adults on selected topics of interest. We then use this system as part of a multi-method approach to investigate the effect of deliberate positivity as a conversational strategy, including its impact on user impressions and willingness to continue using the CA. Our results from different approaches, including methods such as psycholinguistic analysis, user self-report, and researcher-based coding, paint a promising picture of this conversational design. We show that the deliberate encouragement by a CA of positive conversation and reflection in users has a measurable positive impact on both user enjoyment and desire to continue engaging with a system. We further demonstrate how some user characteristics may amplify this effect, and discuss the implications of these results for the design and testing of future conversational systems for older adults.

  PublisherOA PDFDOI

• Geofenced Unmanned Aerial Robotic Defender for Deer Detection and Deterrence (GUARD)

  ArXiv.org · 2025-05-16

  preprintOpen accessSenior author

  Wildlife-induced crop damage, particularly from deer, threatens agricultural productivity. Traditional deterrence methods often fall short in scalability, responsiveness, and adaptability to diverse farmland environments. This paper presents an integrated unmanned aerial vehicle (UAV) system designed for autonomous wildlife deterrence, developed as part of the Farm Robotics Challenge. Our system combines a YOLO-based real-time computer vision module for deer detection, an energy-efficient coverage path planning algorithm for efficient field monitoring, and an autonomous charging station for continuous operation of the UAV. In collaboration with a local Minnesota farmer, the system is tailored to address practical constraints such as terrain, infrastructure limitations, and animal behavior. The solution is evaluated through a combination of simulation and field testing, demonstrating robust detection accuracy, efficient coverage, and extended operational time. The results highlight the feasibility and effectiveness of drone-based wildlife deterrence in precision agriculture, offering a scalable framework for future deployment and extension.

  PublisherOA PDFDOI

• Characterization of brown carbon absorption in different European environments through source contribution analysis

  Atmospheric chemistry and physics · 2025-02-28 · 8 citations

  articleOpen access

  Abstract. Brown carbon (BrC) is a fraction of organic aerosol (OA) that absorbs radiation in the ultraviolet and short visible wavelengths. Its contribution to radiative forcing is uncertain due to limited knowledge of its imaginary refractive index (k). This study investigates the variability of k for OA from wildfires, residential, shipping, and traffic emission sources over Europe. The Multiscale Online Nonhydrostatic Atmosphere Chemistry (MONARCH) model simulated OA concentrations and source contributions, feeding an offline optical tool to constrain k values at 370 nm. The model was evaluated against OA mass concentrations from aerosol chemical speciation monitors (ACSMs) and filter sample measurements, as well as aerosol light absorption measurements at 370 nm derived from an Aethalometer™ from 12 sites across Europe. Results show that MONARCH captures the OA temporal variability across environments (regional, suburban, and urban background). Residential emissions are a major OA source in colder months, while secondary organic aerosol (SOA) dominates in warmer periods. Traffic is a minor primary OA contributor. Biomass and coal combustion significantly influence OA absorption, with shipping emissions also notable near harbors. Optimizing k values at 370 nm revealed significant variability in OA light absorption, influenced by emission sources and environmental conditions. Derived k values for biomass burning (0.03 to 0.13), residential (0.008 to 0.13), shipping (0.005 to 0.08), and traffic (0.005 to 0.07) sources improved model representation of OA absorption compared to a constant k. Introducing such emission source-specific constraints is an innovative approach to enhance OA absorption in atmospheric models.

  PublisherOA PDFDOI

• Diurnal cycle of bioaerosols is a key driver of ice nucleating particle variability for Eastern Mediterranean orographic clouds

  Research Square · 2024-05-20 · 1 citations

  preprintOpen access
  PublisherOA PDFDOI

• WisCompanion: Integrating the Socratic Method with ChatGPT-Based AI for Enhanced Explainability in Emotional Support for Older Adults

  Lecture notes in computer science · 2024-01-01 · 6 citations

  book-chapterSenior author
  PublisherDOI

• Citrus Frost Vulnerability: Exploring the Role of Ice Nucleation Active Bacteria and Temperature Acclimation

  HAL (Le Centre pour la Communication Scientifique Directe) · 2024-08-26

  article

  International audience

  Publisher

• RideKE: Leveraging Low-resource Twitter User-generated Content for Sentiment and Emotion Detection on Code-switched RHS Dataset.

  2024-01-01 · 1 citations

  preprintOpen accessSenior author

  Social media has become a crucial open-access platform for individuals to express opinions and share experiences.However, leveraging lowresource language data from Twitter is challenging due to scarce, poor-quality content and the major variations in language use, such as slang and code-switching.Identifying tweets in these languages can be difficult as Twitter primarily supports high-resource languages.We analyze Kenyan code-switched data and evaluate four state-of-the-art (SOTA) transformerbased pretrained models for sentiment and emotion classification, using supervised and semisupervised methods.We detail the methodology behind data collection and annotation, and the challenges encountered during the data curation phase.Our results show that XLM-R outperforms other models; for sentiment analysis, XLM-R supervised model achieves the highest accuracy (69.2%) and F1 score (66.1%),XLM-R semi-supervised (67.2% accuracy, 64.1% F1 score).In emotion analysis, DistilBERT supervised leads in accuracy (59.8%) and F1 score (31%), mBERT semi-supervised (accuracy (59% and F1 score 26.5%).AfriBERTa models show the lowest accuracy and F1 scores.All models tend to predict neutral sentiment, with Afri-BERT showing the highest bias and unique sensitivity to empathy emotion. 1

  PublisherOA PDFDOI

• Supplementary material to "Characterization of Brown Carbon absorption in different European environments through source contribution analysis"

  2024-07-26

  preprintOpen access
  PublisherDOI

• Characterization of Brown Carbon absorption in different European environments through source contribution analysis

  2024-07-26 · 2 citations

  preprintOpen accessCorresponding

  Abstract. Brown carbon (BrC) is a fraction of Organic Aerosols (OA) that absorbs radiation in the ultraviolet and short visible wavelengths. Its contribution to radiative forcing is uncertain due to limited knowledge of its imaginary refractive index (k ). This study investigates the variability of k for OA from wildfires, residential, shipping, and traffic emission sources over Europe. The MONARCH atmospheric chemistry model simulated OA concentrations and source contributions, feeding an offline optical tool to constrain k values at 370 nm. The model was evaluated against OA mass concentrations from Aerosol Chemical Speciation Monitors (ACSM) and filter sample measurements, and aerosol light absorption measurements at 370 nm derived from AethalometerTM from 12 sites across Europe. Results show that MONARCH captures the OA temporal variability across environments (regional, suburban and urban background). Residential emissions are a major OA source in colder months, while secondary organic aerosols (SOA) dominate in warmer periods. Traffic is a minor primary OA contributor. Biomass and coal combustion significantly influence OA absorption, with shipping emissions also notable near harbors. Optimizing k values at 370 nm revealed significant variability in OA light absorption, influenced by emission sources and environmental conditions. Derived k values for biomass burning (0.03 to 0.13), residential (0.008 to 0.13), shipping (0.005 to 0.08), and traffic (0.005 to 0.07) sources improved model representation of OA absorption compared to a constant k. Introducing such emission source-specific constraints is an innovative approach to enhance OA absorption in atmospheric models.

  PublisherDOI

• EasyCaption: Investigating the Impact of Prolonged Exposure to Captioning on VR HMD on General Population

  Lecture notes in computer science · 2024-01-01 · 4 citations

  book-chapterSenior author
  PublisherDOI

Recent grants

• Auctions for Time-Dependent Tasks

  NSF · $319k · 2004–2009

• NRI-Small: Mixed Human-Robot Teams for Search and Rescue

  NSF · $138k · 2012–2014

Frequent coauthors

• John Collins

  84 shared

• Wolfgang Ketter

  Erasmus University Rotterdam

  66 shared

• Paul E. Rybski

  Carnegie Mellon University

  40 shared

• Paul Schrater

  34 shared

• Giuseppina Gini

  Politecnico di Milano

  33 shared

• Alok Gupta

  30 shared

• S.A. Stoeter

  29 shared

• Dean F. Hougen

  University of Oklahoma

  27 shared

Labs

• Next Generation Robotics LaboratoryPI

Education

• Doctor, Physics

  Universita' degli Studi di Milano

  1972

Awards & honors

• 2025: Presidential Award for Excellence in Science, Mathemat…
• 2024: Diversity, Equity, and Inclusion Leadership Showcase
• 2024: IJCAI Donald E. Walker Distinguished Service Award
• 2022: ACM/SIGAI Autonomous Agents Research Award
• 2019: President's Award for Outstanding Service