Sanjna Ravichandar

Sanjna  Ravichandar
MIT IBM-Watson AI Undergraduate Research and Innovation Scholar
Advisor: Pulkit Agrawal
Department: EECS
Years: 2021-2022
Research Project Title:

Model Free Complex In-Hand Manipulation

abstract:In-hand object manipulation and reorientation is a complex problem because of high dimensional actuation space and change in contact state between the hand and the object. This work presents and implements a model free framework that learns to reorient objects from a given target pose in three maneuvers: with the hand directed upwards, the hand supported on a table, and the hand directed downwards. The model is capable of orienting geometrically different objects in each of the cases, and this project implements the model free framework in simulation as well as leverages transfer learning from real world operations to perform accurately on hardware.

MIT provides so many opportunities for students to work on research alongside professionals and leaders. I have been able to work on projects in several labs at MIT in past UROPs and lab work. SuperUROP now gives me the opportunity to take these past experiences and refine my research skills, thoroughly investigate a problem, and produce my own research to make an impact on the world.