Anushtup Nandy

Designing intelligent autonomous systems.

I'm a Robotics Engineer and Researcher at the intersection of motion planning, reinforcement learning, and control systems and my dream is to be at the frontier of building the next generation of robotic intelligence.

Anushtup Nandy

About Me.

BITS Pilani Hyderabad BITS Pilani
Carnegie Mellon University CMU
Columbia Engineering Columbia

I'm a Robotics Engineer pursuing my MS at Columbia University, with a background in Mechanical Engineering from BITS Pilani. My core passion lies in solving complex problems in robotics, from bio-inspired propulsion to advanced pathfinding algorithms.

My approach combines rigorous analytical principles with creative, hands-on development. I thrive on architecting high-performance algorithms, leading projects from concept to validation, and mentoring teams to achieve ambitious goals.

I bridge the gap between abstract control theory and hardware that actually works in the real world. My work centers on one goal: giving robots the mathematical intuition to navigate complex, high-stakes environments with precision.

Track Record

  • Commercial Impact: At Neocis, I developed dynamic models for the YOMI surgical arm that directly enabled advanced compliant motion and reduced system costs by 20%.
  • Algorithmic Depth: At Carnegie Mellon University, I engineered a novel Heuristic-Search algorithm for pathfinding that outperformed baselines by 2-8x, resulting in two IEEE RA-L publications.
  • Full-Stack Execution: From securing funding for bio-inspired underwater vehicles at BITS Pilani to designing haptic controls for rehabilitation at Columbia's ROAR Lab, I own the entire lifecycle - from first-principles math to hardware deployment.

Core Competencies

Robotics Development

End-to-end project execution from design (CAD, 3D Printing) to control system implementation (ROS, C++, Python).

Algorithm Design

Architecting high-performance algorithms for motion planning (A*) and reinforcement learning (DQN).

Data-Driven Validation

Using advanced instrumentation (NI DAQ, High-Speed Cams) and data analysis (Python, OpenCV) to quantify performance.

Project Leadership

Mentoring junior engineers, securing project funding, and translating engineering solutions into tangible outcomes.

Work Experience.

Jan 2026 - Present

Control Systems Engineer

ARMATRIX · Full-time

At ARMATRIX, I am architecting the core software framework for the robotic arm, defining the system-level hierarchy to ensure scalable control and navigation. This includes developing and deploying Sequential Convex Programming (SCP) and QP-based soft-constrained MPC algorithms, enabling high-fidelity navigation through narrow gaps and high-obstacle density environments. Additionally, I am engineering a high-fidelity dynamic simulation environment in MuJoCo, bridging the Sim2Real gap through detailed physics modeling and system identification to accelerate control tuning.

🎯 Strategic Career Move

Following my time at Columbia and CMU, I’ve chosen to return to India to focus on deep-tech robotics. For me, this move is about prioritizing engineering substance over geography. My experiences in the US, from developing surgical robotics to engineering advanced pathfinding algorithms, honed my ability to bridge first-principles math with real-world hardware deployment. I’m excited to bring that technical rigor home to solve complex problems and contribute to the growth of India’s robotics ecosystem.

Bringing learnings from the USA back home

May 2025 - Aug 2025

Robotics Intern

Neocis Inc.

As a Robotics Intern at Neocis, I engineered an analytical dynamic model for the 7-DOF YOMI surgical robot arm, leveraging RNEA, CRBA, and System ID techniques. This high-fidelity model was instrumental in implementing Computed Torque control, which enabled advanced compliant behaviors. My contributions directly supported a strategic initiative to reduce the YOMI's production cost by 20%. I also designed critical CAD models for PCB fixtures to integrate new encoders into the arm's control system.

Mar 2023 - Dec 2023

Student Research Intern

Carnegie Mellon University

During my research internship at Carnegie Mellon University, I architected and implemented a novel Heuristic-Search algorithm in C++ to solve resource-constrained shortest path problems. By incorporating advanced techniques like dominance criteria and partial path pruning, my solution achieved a 2x performance increase over the existing baseline. Moreover, I also worked on testing algorithms developed by a colleague and to validate these findings in a real-world context, I developed a ROS2 framework to benchmark my algorithm against others, proving its superior efficiency in autonomous systems.

June 2022 - July 2022

Design Intern

Pacify Medical Technologies

At Pacify Medical Technologies, I led the design of a compact syringe-gun injection mechanism. Using SolidWorks, I engineered a new holder and nozzle assembly that achieved a 25% reduction in size. To enhance device reliability, I integrated a force-sensitive resistor with an Arduino to provide active load measurement, effectively preventing breakage under operational stress. My role also involved collaborating with suppliers to source materials, which successfully reduced a potential budget overrun by 5%.

Selected Projects.

A collection of my work spanning robotics, AI/ML, and autonomous systems.

Robotics

Transformer-based MPC for 7DoF Arm

Developed a transformer-based Model Predictive Controller for real-time trajectory optimization of a 7-DOF robotic arm, enabling adaptive and precise manipulation.

TransformersMPCControl Theory
Research

Heuristic Search for RSCPP

Developed an A*-like algorithm in C++ to solve resource-constrained shortest path problems with fuel constraints, outperforming baselines by 2-8x.

C++Motion PlanningROS2
AI/ML

Agentic Personal Assistant Team

Multi-agent system with specialized AI agents working collaboratively to handle diverse personal assistant tasks using LLMs and tool-based reasoning.

Multi-Agent SystemsLLMsRAG
Web

ScholarSync

Collaboration platform for researchers featuring real-time document editing, reference management, and automated citation formatting for academic teams.

ReactWebSocketsMongoDB
Robotics

Bio-Inspired Undulatory Fin

Designed a robotic fin mimicking stingray motion for efficient, low-acoustic underwater propulsion, securing ₹2 lakhs funding.

ArduinoCADControls
AI/ML

NeuroSymbolic AI Research

Combining neural networks with symbolic reasoning to create hybrid AI systems capable of both learning from data and logical inference.

Neural-SymbolicLogicPyTorch
Web

VitalMesh

Intelligent healthcare communication with AI voice agents for triage, real-time EHR integration, and multi-agent processing using Coral MCP protocol.

HealthTechMCPVoice AI
AI/ML

Tribal Knowledge Vision

Computer vision system for capturing and digitizing tacit manufacturing knowledge, enabling knowledge transfer and process optimization in industrial settings.

Computer VisionOpenCVKnowledge Capture
Robotics

Haptic Joystick Control

Developed a PD-based haptic control system for a rehabilitation robot, enabling remote therapy for SCI patients.

HapticsControlsHRI
AI/ML

Asclios

AI-driven health monitoring system integrating wearable sensor data with predictive analytics for personalized wellness insights.

IoTMLData Analytics
Robotics

Stewart Platform Kinematics

Interactive 3D visualization tool for 6-DOF parallel manipulator with real-time IK solver and stability analysis.

Parallel KinematicsControlStability
AI/ML

Cognitive Digital Twin

AI-powered digital twin framework for real-time manufacturing optimization using LLMs and reinforcement learning for adaptive decision-making.

Digital TwinLLMsRL
Research

Path Planning via Deep RL

Formulated a DQN-based planning algorithm for mobile robots in unknown environments, leading to an ACM AIR 2023 publication.

Reinforcement LearningPyTorch
Web

Sunnovation Platform

Web application for solar energy optimization and monitoring with real-time analytics and predictive maintenance features.

ReactIoTAnalytics
Research

Validation of DMS* & MS*

Validated combinatorial search algorithms on ROSbots, proving DMS* is 2x faster by better distributing intermediate targets.

Path PlanningROS
AI/ML

Image-2-3D Reconstruction

Deep learning pipeline for generating 3D models from 2D images using neural radiance fields and diffusion models.

NeRFDiffusion Models3D Vision
AI/ML

Local LLM Personal Assistant

Privacy-focused personal assistant running LLMs locally with tool integration, knowledge base, and task automation capabilities.

LLMsLocal InferenceOllama
Robotics

Single Legged Raibert Hopper

Designed a Raibert Hopper in URDF and implemented a PID controller for balance and navigation using an inverted pendulum gait.

Legged RoboticsControlsURDF
Robotics

Delta Parallel Robot

Developed a Delta robot from concept to hardware using 3D printing, acrylics, and a PID controller with an Arduino Mega.

Parallel RoboticsCADArduino
AI/ML

LLM Aero Input Generator

LLM-based tool for generating CFD simulation inputs and parameter configurations for aerospace applications using natural language.

LLMsCFDCode Generation

Publications.

Heuristic Search for Path Finding With Refuelling

S. Zhao, A. Nandy, H. Choset, S. Rathinam and Z. Ren
IEEE Robotics and Automation Letters, vol. 10, no. 4, April 2025

PDF

Maze Solving Using Deep Q-Network

Anushtup Nandy, Subash Sehsashtri, Abhishek Sarkar
Advances In Robotics - 6th Intl. Conference of The Robotics Society (AIR 2023)

PDF

DMS*: Towards Minimizing Makespan for Multi-Agent Combinatorial Path Finding

Zhongqiang Ren, Anushtup Nandy, Sivakumar Rathinam, and Howie Choset
IEEE Robotics and Automation Letters 9.9 (2024)

PDF

Get In Touch.

I'm always open to discussing new projects, research, or potential collaborations. Feel free to reach out.