I am...
a PhD student at Rensselaer Polytechnic Institute, Troy, New York. As a part of Center for Mobility with Vertical Lift (MOVE), my research is focused towards developing a stochastic framework for fault detection and identification (FDI) techniques in Urban Air Mobility platforms.
I have received the Amelia Earhart Scholarship in 2020 and the Vertical Flight Society Fellowship in 2021, for my outstanding research in Aerospace engineering. My vision is materializing future artificial intelligence enabled cyber-physical vehicles that will be able to “feel,”“think,” and “react” in real time. To achieve that, I intend to collaborate with magnificent minds all over the world whose collective vision is to know, find and figure things out for building a sci-fi fantasy world for humankind
I am currently working on...
Physics Augmented Statistical Learning framework for Fault Detection and Identification on potential Urban Air Mobility platforms
Urban air mobility, enabled by autonomous electric VTOL (eVTOL) aircraft, has been identified as a revolutionary solution to avoid roadway congestion in major cities. A NASA sponsored study reported urbanair mobility to be viable and assessed its available market value at $500B. But, its operational success in dense urban environments will require real-time system-level awareness and safety assurance, making real-time fault detection and identification (FDI) of such systems critical for optimal control reallocation or vehicle reconfiguration to complete flight safely. I am exploring physics-augmented machine learning framework for incorporating self-sensing, self-awareness and optimal decision-making capabilities under disturbances and uncertainty in potential Urban Air Mobility platforms.
The vision is realizing future intelligent and autonomous vehicles will be able to ``feel,'' ``think,'' and ``react'' in real time based on high-resolution state-sensing, awareness, and self-diagnostic capabilities allowing for superior performance, adaptability, resilience, increased safety, optimal control, reduced maintenance costs, and complete life-cycle monitoring and management.
Time-series Assisted Neural Network
Learn the healthy dynamics from aircraft states and controller commands time series data
Formulate a feature capable of distinguishing aircraft response to gusts from that due to rotor faults
Rotor fault classification and fault level determination with a simple neural network
A Probabilistic framework for Sensor Fusion
"The whole is greater than the sum of its parts"- Aristotle
Effective predictive maintenance needs exploitation of multimodal data streams provided by many different sensors
The aim of this work is to integrate the sensors locally and globally in an probabilistic framework, to augment the reliability of the decision making algorithm while simultaneously accounting for sensor malfunction
More about me...
I completed Masters in Mechanical Design from Indian Institute of Technology, Delhi in 2017. There I was felicitated by Rural Technology Action Group, IIT Delhi on behalf of Office of the Principal Scientific Adviser to the Govt. of India, for developing Solar-operated Treadle pump for farmers in India, as part of my Masters thesis.
My other interests expanses multibody dynamics, control, robotics, device development and advanced mechanisms. I have a varied research experience ranging from rural technologies to rehabilitation robotics, working with marginal artisans and farmers of India to children with locomotor disability. I have focused on developing a working prototype as the end goal of most of my projects.
Apart from research, I am trained in Indian Classical Music and have great fascination in art and history.