Seed Grants

Grant Winners

• Joo H. Kim, Associate Professor of Mechanical and Aerospace Engineering, NYU Applied Dynamics and Optimization Laboratory
• Qi Sun, Assistant Professor of Computer Science and Engineering, NYU Immersive Computing Lab 

Project Description

Deployment of robots that are typically controlled by automated algorithms or remote devices (keyboards, joysticks) is not suitable for tasks in complex urban environments. In this project, for the purpose of exploiting human’s sensing, decision making, and action through intuitive interactions, a humanoid robot will be used to sense and stream back a scene, and serve as a remote avatar to accomplish a task through AR-sensed and automatically interpreted commands from the user. This project will develop methods of low-latency streaming and immersive visualization of scene data and establish predictive mapping and control for robot loco-manipulation through user-in-the-loop extended reality.

Grant Winners

• Constantine Kontokosta, Associate Professor of Urban Science and Planning, Marron Institute

Project Description

The COVID-19 pandemic has rapidly accelerated the increase in remote work and spurred new labor relations that are almost certain to make it a permanent feature of American cities. The proposed research (with Prof. Solly Angel and researcher Bartosz Bonczak) aims to use mobility data to analyze the spatial and temporal patterns of space use and the connections between commercial districts and residential areas. The study will provide a deeper understanding of how mobility behaviors and use of space are shifting in response to the changing nature of work in U.S. cities. The data processing and analysis proposed here are expected to provide a useful foundation for future applied and fundamental research studies.

With support from the Department of Technology Management and Innovation

Grant Winners

• Graham Dove, Research Assistant Professor of Technology Management and Innovation, NYU Tandon

Project Description

This project will support vulnerable communities in Chinatown in monitoring environmental pollutants caused by the demolition of the Manhattan Detention Complex (MDC), and in data-driven activism for health and environmental justice. Based on a participatory program of community-based citizen science, the project leverages existing intergenerational programs connecting after-school activities organized by Immigrant Social Services with residents at Chung Pak Senior Housing. Both these community-based organizations occupy space in a building that shares a wall with MDC and will be directly impacted by demolition work. Project partners include NYU Center for the Study of Asian American Health, Chung Pak LDC, the Chinese-American Planning Council, Hamilton Madison House, and the Neighbors United Below Canal.

With support from the NYU Sustainable Engineering Initiative 

Grant Winners

• Elizabeth Henaff, Assistant Professor, Technology, Culture and Society, NYU Tandon

Project Description

An environmental microbiome is defined as the population of micro-organisms that inhabit a specific environment. A growing body of literature shows that low microbiome diversity exposure has been linked to negative health outcomes. Thus, access to diverse environmental microbiomes is a question of environmental justice. This pilot study will prototype a methodology for co-evaluation of  spatiotemporal environmental conditions and microbial metrics to observe the dynamics of airborne microbial colonies within an urban microclimate of New York City. We hypothesize that urban microbial diversity metrics correlate with area-level conditions that constitute environmental and social justice metrics.

With support from the NYU Sustainable Engineering Initiative 

Grant Winners

• Semiha Ergan, Civil and Urban Engineering, NYU Tandon

Project Description

The goal of this project is to develop a framework that can adapt to buildings even with minimum Building Automation System (BAS) equipment to train optimized building HVAC systems with high energy efficiency. Building energy consumption represents one-third of the United States’ greenhouse gas (GHG) emissions, the largest of any sector (EPA, 2021). Ranked as the largest end-use type for building energy consumption, HVAC represents approximately one-third of energy consumption in residential buildings and 17% in commercial buildings. (EIA, 2021) For the optimization of building energy consumption, our project adopts a machine learning (ML) based deep reinforcement learning (DRL) method to develop a pipeline to input key operational parameters from available BAS data at the subunit level to output optimized control of building energy consumption. We expect the model application will lead to up to 20 to 30% energy savings from HVAC systems by operational control alone.