Greetings, I am a MS Robotics student at Georgia Tech, where I do household robot learning research under Prof. Sonia Chernova in the RAIL lab and dexterous manipulation under Prof. Animesh Garg in the PAIR lab.

My research interests lies in curiosity-driven reinforcement learning, interactive robot learning, semantic mapping, and dexterous manipulation. I aim to apply these methods to assistive and household robots that must learn in dynamic, human-centric environments.

Previously, I completed my BS in Robotics Engineering and Computer Science at Worcester Polytechnic Institute (WPI), where I worked with Prof. Carlo Pinciroli on swarm robotics and multi-agent communication at Nest lab.

Email  /  GitHub  /  LinkedIn

profile photo
Research
FLASH
FLASH: Flow-Based Language-Annotated Grasp Synthesis for Dexterous Hands
H. Leen, J. A. Collins, K. Aneja, N. Nguyen, P. Tamilselvan, S. S. Chakaravarthy P, A. Garg
CoRL 2025 Workshop Dexterous Manipulation Spotlight
Dexterous Manipulation Flow Models

A method for language-conditioned dexterous grasping that jointly models task intent and physical contact quality for robot hands.

StretchMapping
StretchMapping: Semantic Mapping for Mobile Manipulators
H. Muriki, N. Nguyen, R. Rustagi, M. Patel, K. Ramachandruni, S. Chernova
Hello-Robot Newsletter, April 2025
Semantic Mapping Dynamic Environments

An open-source system for mobile manipulators that builds and updates semantic maps of large, dynamic environments. By integrating ORB-SLAM2, semantic segmentation, and the Khronos mapping pipeline, it tracks moving objects and people over time, enabling long-term scene understanding.

Survey
Deep Learning for Dexterous Manipulation: A Survey and Benchmark
In review journal, Advanced Robotics Research
Survey Dexterous Manipulation Reinforcement Learning

A comprehensive survey of deep learning approaches for dexterous robotic grasping, emphasizing recent progress enabled by multi-modal models and data-driven techniques.

SGCode
SGCode: A Flexible Prompt-Optimizing System for Secure Generation of Code
K. Ton, N. Nguyen, M. Nazzal, A. Khreishah, C. Borcea, N. Phan, R. Jin, I. Khalil, Y. Shen
ACM CCS 2024, Co first author
LLMs Internship Security

A flexible prompt-optimizing system for generating secure code with LLMs. SGCode integrates prompt-optimization approaches with security tools and a lightweight generative adversarial graph neural network to detect and fix vulnerabilities in generated code.

Projects
HINTeract
HINTeract: A Hierarchical Interactive Learning Framework for Robotic Manipulation
Manipulation Reinforcement Learning

A hierarchy RL policy that enables robots to actively seek human guidance through hints rather than full demonstrations to recover from mistakes before total failure. I proposed the idea and implemented the framework in Robosuite. I will revisit this at some point.

Cable Robot
Multi-Cable Robot Planning for Agriculture Data Capture
Reinforcement Learning Multi-Agents

Reinforcement learning implementations for cable-driven parallel robots designed for agricultural monitoring and inspection tasks.

Mailman Medium
Decentralized Mailman Medium Communicator
Multi-Agents Wireless Communications

Proposing and implementing a range and bearing communication method that allows robots to use real-life and simulation sensors in a simulated environmen for the ARGoS3 open-source multi-agent simulations. It was my first time using the Vicon motion capture system!

Ball Sorting Arm
Vision-Guided Ball Sorting Arm
Manipulation Computer Vision

Built a vision-guided manipulation system that detects colored balls, localizes them in 3D, and performs reliable pick-and-place sorting using forward/inverse kinematics and motion control.

Romeo and Julibot
Romeo and Julibot
Wireless Communications Built Robots Computer Vision

An autonomous multi-robot reenactment of Romeo and Juliet, using MQTT communication, IMU collision detection, ultrasonic sensing, ICC kinematics, and AprilTag tracking to coordinate scene-based behaviors.

SLAM Navigation
SLAM Mapping Navigation for Path Finding
SLAM Mapping ROS2

Deployed a TurtleBot3 in an unknown maze environment, utilizing particle filter localization and A* path planning while continuously updating its uncertainty model to enable robust autonomous navigation-validated both in simulation and real-world scenarios.

Humanoid Robot
Custom Multi-Purpose Humanoid
Hardware Middleware

Manufactured the physical body for a custom humanoid robot and developed an open-source middleware bridging low-level motor control with high-level controllers, following agile development practices and clean code principles.

Apart from robotics, I also like to do digital arts, play with electronics, a LEGO enthusiast and trying to get higher rank in Kendo! See more →

× Poster
×