Back to Portfolio
Download PDF

Arnav Chopra

Education

New York University

Master of Science in Mechatronics and Robotics — GPA: 3.75 / 4.0

Bachelor of Science in Mechanical Engineering — GPA: 3.7 / 4.0

Honors: Dean's List 2021 – 2024

Coursework: Reinforcement Learning, Robot Locomotion, Computer Vision, Control Systems, Mechatronics, FEA

New York, NY M.S.: May 2026 B.S.: May 2025

Technical Skills

Machine Learning & AI Reinforcement Learning, Vision-Language Models (VLM), Agentic Evaluation, PPO, SAC, PyTorch, TensorFlow, Reward Function Design, Domain Randomization, Error Analysis
Computer Vision & Robotics OpenCV, YOLOv8, MediaPipe, Visual SLAM, RRT Motion Planning, Extended Kalman Filters (EKF), Particle Filters, ROS2, Isaac Lab, NYU Greene (HPC Cluster)
Controls & Hardware System Modeling, LQR, MPC, PID, Arduino, Raspberry Pi, NVIDIA Jetson Orin
Languages Python, C++, MATLAB

Industry Experience

Computer Vision Intern
HCL Technologies
  • Developed an end-to-end perception pipeline utilizing OpenCV and YOLOv8 to detect safety equipment and objects within real-world quick service restaurant environments.
  • Trained and evaluated object detection models across challenging environmental variances (lighting, occlusions, viewpoints) to achieve a baseline mAP50 of 52%.
  • Integrated perception framework outputs into system-level execution logic, verifying real-time operational reliability.
Mechanical Design Intern
InnovFusion Tech
  • Conducted Finite Element Analysis (FEA) on structural components to evaluate stress distribution, fatigue, and deformation.
  • Iterated physical designs based on simulation analytics, successfully increasing component lifecycle by 126% and reducing maximum operational stress concentrations by 22%.

Core AI & Robotics Projects

Visual Anomaly Detection & VLM Safety Evaluation
  • Co-developed the Obstacles Out-of-Place Scoring (OOPS) framework to systematically evaluate the spatial reasoning, safety compliance, and contextual understanding of Vision-Language Models (VLMs) in navigation tasks.
  • Curated a structured dataset of real-world scene anomalies to stress-test models including ChatGPT, Gemini, and InternVL.
  • Performed rigorous error analysis to isolate systemic model failure modes, spatial inconsistencies, and overconfidence trends, formulating concrete optimization strategies for human-aligned, risk-aware AI evaluation.
Skills: Vision-Language Models (VLM), Spatial Reasoning, Error Analysis, Dataset Curation
Quadruped Robot Locomotion via Reinforcement Learning
  • Trained robust locomotion policies for a Unitree Go2 quadruped within NVIDIA Isaac Lab, deploying scalable training pipelines across the NYU Greene High-Performance Computing (HPC) cluster.
  • Designed multi-objective reward structures targeting precise foot placement, torque smoothness, slip reduction, and balance.
  • Applied domain randomization over irregular terrains, velocity commands, and external forces to ensure broad policy generalization.
Skills: Reinforcement Learning, Isaac Lab, PyTorch, High-Performance Computing (HPC), Python
Multi-Link Inverted Pendulum Stabilization via RL
  • Implemented and cross-evaluated Proximal Policy Optimization (PPO) and Soft Actor-Critic (SAC) reinforcement learning algorithms to balance a multi-link dynamic inverted pendulum system on a cart in NVIDIA Isaac Lab.
  • Designed targeted reward formulations to maximize upright stability, eliminate transient oscillations, and penalize excessive control effort.
Skills: Reinforcement Learning, PPO, SAC, Isaac Lab, Reward Design
Real-Time Gesture Recognition & Robotic Command Pipeline
  • Built a low-latency, vision-based hand gesture recognition pipeline processing live camera feeds to map human intent directly to physical robotic control coordinates.
  • Utilized MediaPipe and OpenCV to isolate hand landmarks and classify spatial patterns reliably under varying illumination.
Skills: Computer Vision, MediaPipe, OpenCV, Python

Academic Experience

Course Assistant – Machine Design and Structures Practicum
NYU Department of Mechanical and Aerospace Engineering
  • Provide direct technical guidance and lab supervision to undergraduate students; manage objective grading metrics for assignments and quizzes under strict confidentiality guidelines.