Resume-aware faculty matching

Find professors who actually fit you

Review faculty evidence in public, then use the workspace to turn your background into a shortlist, outreach, and meeting prep.

Profile-awarePaper evidenceSix agents
Vijay Kumar

Vijay Kumar

· Professor Nemirovsky Family Dean

University of Pennsylvania · Computer Science

Active 1967–2025

h-index67
Citations23.1k
Papers953318 last 5y
Funding$8.4M

Academic metrics are sourced from OpenAlex and public funding records; values may differ from Google Scholar.

See your match with Vijay Kumar — sign in to PhdFit.Sign in

About

VIJAY KUMAR is the Nemirovsky Family Dean of Penn Engineering with appointments in the Departments of Mechanical Engineering and Applied Mechanics, Computer and Information Science, and Electrical and Systems Engineering at the University of Pennsylvania. His group works on creating autonomous ground and aerial robots, designing bio-inspired algorithms for collective behaviors, and on robot swarms.

Research topics

  • Computer Science
  • Artificial Intelligence
  • Machine Learning
  • Pathology
  • Medicine
  • Data science
  • Algorithm
  • Radiology

Selected publications

  • Vision Transformers for End-to-End Vision-Based Quadrotor Obstacle Avoidance

    2025-05-19 · 9 citations

    articleSenior author

    We demonstrate the capabilities of an attentionbased end-to-end approach for high-speed vision-based quadrotor obstacle avoidance in dense, cluttered environments, with comparison to various state-of-the-art learning architectures. Quadrotor unmanned aerial vehicles (UAVs) have tremendous maneuverability when flown fast; however, as flight speed increases, traditional model-based approaches to navigation via independent perception, mapping, planning, and control modules breaks down due to increa…

  • Observations on the Effect of Artificial Lights on Foraging Behaviour of Greater Shot-Nosed Fruit Bat, <i>Cynopterus sphinx</i> (Vahl, 1797) in Babasaheb Bhimrao Ambedkar University Campus, Lucknow, India

    Records of the Zoological Survey of India · 2025-02-05 · 2 citations

    article1st authorCorresponding

    Excess illumination from artificial lighting poses a serious hazard to nocturnal species, particularly flying nocturnal creatures. Bats possess excellent active flight with highly adapted limbs. All bat species are entirely nocturnal and have quite distinct feeding patterns and foraging strategies. Cynopterus sphinx is a medium-sized bat that feeds on ripe fruits, leaves, and floral parts available in foraging grounds on a variety of plant species and plays a significant role in pollination and…

  • Machine learning-driven strategies for optimal design of heating, ventilation, and air-conditioning (HVAC) filter media

    Separation and Purification Technology · 2025-08-31 · 1 citations

    articleOpen access

    • ML models predicted the filtration efficiency and pressure drop of HVAC filter media. • GPR outperforms ANN and DT, achieving highest R 2 and lowest RMSE for small datasets. • GPR predicted filtration efficiency at Most Penetrating Particle Size (∼300 nm) • Robustness of GPR predictions confirmed via validation with commercial HVAC filters. The COVID-19 pandemic has highlighted the critical need to improve indoor air quality (IAQ) through efficient air filtration, especially in heating, ventil…

  • “Fraud Detection in Financial Transactions Using Pyspark on Databricks”

    INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT · 2025-06-11

    articleOpen access1st authorCorresponding

    Abstract - In the era of digital finance, detecting fraudulent transactions is a major concern for financial institutions. Fraudulent activity not only results in monetary losses but also erodes customer trust. This project proposes a scalable and efficient system for fraud detection in financial transactions using PySpark on the Databricks platform. The core idea is to leverage the power of distributed data processing with PySpark to train machine learning model capable of identifying potential…

  • Applications of MCDM Aggregation Operator in the Selection of Suitable Site for the Manufacturing Plant

    Apple Academic Press eBooks · 2025-09-17

    book-chapter1st authorCorresponding

    The development of multicriteria decision-making (MCDM) techniques helps in the decision-making process and addresses many real-life problems. In this chapter, an intuitionistic fuzzy-based MCDM decision-making technique has been proposed for the selection of a suitable site for a manufacturing plant. Dynamic intuitionistic fuzzy weighted averaging operator has been used for decision-making under an intuitionistic fuzzy environment. The method is demonstrated by the help of a case study, compris…

Recent grants

Frequent coauthors

  • Pradeep Das

    National Institute of Cholera and Enteric Diseases

    68 shared
  • Dilbag Singh

    44 shared
  • Amit Rawal

    Indian Institute of Technology Delhi

    37 shared
  • Dinesh Kumar

    Delhi Technological University

    31 shared
  • Shreekant Kesari

    Rajendra Memorial Research Institute of Medical Sciences

    31 shared
  • Daniel Ekwall

    Hanken School of Economics

    29 shared
  • Ludovic Koehl

    Laboratoire Génie et Matériaux Textiles

    28 shared
  • Xianyi Zeng

    École Nationale Supérieure des Arts et Industries Textiles

    28 shared

Labs

Education

  • Ph.D., Mechanical Engineering

    University of California, Berkeley

    1990
  • M.S., Mechanical Engineering

    University of California, Berkeley

    1986
  • B.S., Mechanical Engineering

    University of California, Berkeley

    1984

Awards & honors

  • Fellow of ASME
  • Fellow of IEEE
  • Elected to the National Academy of Engineering
  • Elected to the American Philosophical Society
  • Elected to the American Academy of Arts and Sciences

Similar researchers at University of Pennsylvania

  • Resume-aware match score
  • Save to shortlist
  • AI-drafted outreach

See your match with Vijay Kumar

PhdFit ranks faculty by your research interests, methods, and publications — grounded in their actual work, not templates.

  • Free to start
  • No credit card
  • 30-second signup