Professor Projects

Project Name: Interface Development for Quantum Sensing Apparatus
Project Instructor: Prof. Kasturi Saha
Domains: Sensor Interfacing, GUI development, Quantum Sensing
Project Description: The PQuest lab at IIT Bombay works in the domain of quantum sensing. The lab uses sophisticated programming and sensors to acquire data from experiments. Currently, this is done by running scripts such that the data is recorded but can only be seen once the experiment is over. There is an urgent need to convert the functioning codebase to a GUI environment for faster experimentation and to allow the real-time visualization of the recorded data. 

Project Name: Pavement Condition Index (PCI): Automation for Road Development

Partner: Government of Maharashtra, Project UMA (https://www.ctara.iitb.ac.in/en/uma)

Sectors: Transportation

Category: Data Analytics, Software Development

Current Team:

• Professor-in-charge: Milind Sohoni
• Project Team: Project UMA Leads (Gopal, Chirag)

Description: There exists no systematic way to centrally organize road development in Maharashtra, and much of India. This project aims to contribute to change this by automating the assessment of road pavement conditions. This will be achieved by collecting data from various in-buillt smartphone sensors such as accelerometers and GPS, as well as textual inputs like pothole counts, to compute the Pavement Condition Index (PCI). The PCI will serve as a key parameter to inform budget allocation and road quality improvement strategies. The project involves the development of a mobile app for data collection, the creation of a central database for storage and analysis, and the formulation of a data model to relate raw sensor data to the PCI.

Project Name: Testing of Novel Rocket Fuels

Category: Mechanical Engineering

Sub-category: Core

Professor-in-charge: Neeraj Kumbhakarna

Description: This project involves experimental testing of combustion of newly synthesised liquid rocket fuels to evaluate their performance.

.

Project Name: ML-Driven Optimisation of Rocket Fuel Oxidisers

Category: Mechanical Engineering

Sub-category: Energetic Materials, Machine Learning

Professor-in-charge: Neeraj Kumbhakarna

Description: This project aims to use machine learning tools to generate new energetic molecules for rocket fuel oxidisers, with the purpose of enhancing the efficiency of fuel-related processes, particularly in the field of rocket propulsion. The potential of ML in fuels and combustion is still to be fully explored; the project seeks to fill this gap, first through theoretical methods and then through practical implementations.

Project Name: Project on Climate Resilient Agriculture

Partner: Department of Agriculture (DoA), Government of Maharashtra

Sectors: Agriculture, Energy

Category: Computer Science, Agriculture/Water Management

Project website: https://mahapocra.gov.in/

Current Team:

    - Professor-in-charge: Milind Sohoni, Priya Jadhav

    - Senior IT/project experts: Hemant, Asim

    - Team: Satish

Description: Climate variability and extreme weather events pose serious challenges to farmers’ agricultural productivity and livelihoods across central Maharashtra, one of the most environmentally sensitive regions in India. Smallholder farmers here face a range of issues related to water management, energy access, and other critical inputs that affect their ability to produce crops profitably.

We seek to address these challenges by leveraging technology and scientific research to develop scalable tools and advisory services that provide farmers with accurate information about water and energy management. Ultimately, our grand vision is to empower farmers and decision-makers alike with the tools and knowledge necessary to build a sustainable and thriving agricultural sector in central Maharashtra, one that can adapt and thrive in the face of climate change and other environmental challenges.

Project name: Optimising MSRTC Operations through Network Modeling and Social Metrics

Partner: Maharashtra State Road Transport Corporation (MSRTC)

Sectors: Public Transport, Optimization, Social Value Accounting

Category: Computer Science

Current Team:

    - Professor-in-charge: Milind Sohoni

    - Senior IT expert: Rahul

    - Team: Rijyuta, Ashutosh, Satyam

Description: The MSRTC, a pivotal element of Maharashtra's transport infrastructure, operates as the primary regional public bus system. Nevertheless, the corporation confronts various hurdles in terms of effective decision-making and operational efficiency. These include determining optimal routes to enhance coverage and efficiency, allocating buses to routes on a daily basis, and more.

In simple words, the organization incurs losses amounting to hundreds of crores every year, which affects its service delivery and causes hardship to a significant section of people. However, we are confident that by implementing a range of measures, including the development of an IT stack, social and financial value accounting, and strategic optimizations, we can considerably enhance the MSRTC's operations. An MoU between IITB and MSRTC has already been established.

The foundation of the proposed IT stack is the network layer, which is a directed graph consisting of nodes and edges that represent the road network. This layer includes essential attributes on both nodes and edges, forming the basis for the development of a geospatial computation framework. To aid decision-making at select depots, we plan to create and deploy software tools. Furthermore, we will establish a methodology for social value accounting and implement it in specific depots.

Project Name: Modernising Land Records

Partner: Directorate of Land Records (DoLR), Govt. of Maharashtra and Google Research

Sectors: Land Records

Category: Computer Science

Current Team:

    - Professor-in-charge: Milind Sohoni

    - Senior IT expert: Asim

    - Student team: Aaryan, Lisan, Yash, Manav

Description: The Government of Maharashtra is looking to modernize land records, and create geo-referenced (latitude-longitude) ownership plots that are as close a match to ground reality as possible. There are several resources we have at our disposal: village paper maps that often date back to the 1800s, satellite images segmented into polygons that represent distinct farm plots (provided by Google), and some other textual/geometric data for each survey plot.

The central problem we face is that the old paper-based maps don’t match the actual farm boundaries that currently exist; rivers have changed paths, ownership of land has been subdivided, and, most importantly, the old techniques of mapping weren’t precise at all, especially by today’s standards. Hence, there is no one legal map for any village: this is not good news, given the number of legal disputes currently awaiting resolution.

Hence, our task is to take the space partitions of polygons, that is the survey map, first digitized and scaled appropriately, and transform it mathematically (using operations such as rotations, translations, node shifts, etc) to match farm plot boundaries while ensuring minimum deviation in parameters such as area/shape index.