PROJECTS

Welcome to my projects portfolio, where I showcase my journey in AI and Robotics. Each project represents a step in my exploration of cutting-edge technologies and innovative solutions. From deep learning for long-horizon manipulation planning and reinforcement learning to quadrotor control and multi-agent planning, I am passionate about creating systems that push the boundaries of what's possible.
Click on a project to learn more!

Quadrotor Landing on an Unstable Mobile Platform

Designing and Implementing Model Predictive Control to make a quadrotor land on an unstable moving platform

ML-EECBS - Estimating better MAPF heuristics

Using ML methods to improve Explicit Estimation Conflict Based Search, a S.O.T.A. Multi-Agent Path Finding Algorithm

IROS 2024

SculptDiff: Diffusion policy for robotic sculpting

Developed a goal-conditioned diffusion-policy based imitation learning framework for deformable object manipulation

Deep RL for Aerobraking
Maneuvers

Trained a Proximal Policy Optimization Agent to perform aerobraking maneuvers faster and with reduced fuel consumption

Multi-Agent Pathfinding Algorithms

Implemented S.O.T.A. Multi-Agent Path Finding Algorithms (PP, CBS, PBS, EECBS) and evaluated their performances

Sq_Flatten_the_dough_and_stab_it-ezgif.com-optimize.gif

Planning with LLMs for Robotic Manipulation

Designed an Agentic LLM Framework to identify object locations within a scene, generate a high-level plan, and execute this plan through a series of low-level actions