Available for Summer / Full-Time '26 Boston, MA

Mayank Goud
Polagoni.

Computer vision & reinforcement learning researcher — building perception systems that see, track, and decide. Currently a graduate student at Northeastern University, working at the intersection of deep learning, real-time tracking, and autonomous control.

Focus
Computer Vision
Program
MS Computer Science
Institution
Northeastern
Graduating
Spring 2027
/ 01

About the work.

I work on the parts of vision systems that have to be right in real time — detection, tracking, and the geometry that ties pixels back to the physical world.

My research combines classical computer vision — feature descriptors, calibration, multi-view geometry — with modern deep learning pipelines for detection, tracking, and recognition. I care about systems that hold up outside benchmarks: latency budgets, occlusion, domain shift, the unglamorous failure modes.

On the RL side, I've trained PPO, SAC, and TD3 agents in the F1TENTH autonomous racing simulator, comparing them against classical control baselines. I'm drawn to problems where perception meets control — where a model has to look at the world and act on it before the next frame.

Outside the lab: Formula 1, Marvel marathons, and exploring Boston.

/ 02

Selected work.

001
CS 5330 · Final Project

Real-time Multi-Object Tracking

Built a tracking pipeline from scratch combining YOLOv8n detection, a custom Kalman Filter for motion prediction, and the Hungarian algorithm for data association. Custom association logic was implemented end-to-end to satisfy original-contribution requirements. Delivered an IEEE-format report and live demo.
YOLOv8Kalman FilterHungarianPythonOpenCV
002
CS 5180 · Final Project

Deep RL for Autonomous Racing

Comparative study of PPO, SAC, and TD3 against classical control baselines in the F1TENTH autonomous racing simulator. Investigated sample efficiency, stability, and lap-time performance under varying reward shaping. Published as a publication-quality report in AAAI two-column format.
PPOSACTD3F1TENTHPyTorch
003
CS 5330 · Project 5

Deep Learning Vision Pipeline

End-to-end image recognition pipeline: CNN baseline, Vision Transformer fine-tuning, and Gabor filter feature extensions for comparative analysis. Reported with full ablations and a Word-compatible technical writeup.
CNNViTGabor FiltersPyTorch
004
CS 5330 · Project 4

Camera Calibration & AR

C++ / OpenCV implementation of intrinsic camera calibration and real-time augmented reality overlays. Four extensions including animated 3D scenes and keyboard-controlled virtual objects projected onto a checkerboard pattern.
C++OpenCVARCalibration
005
CS 5180 · Coursework

Deep RL Algorithms in PyTorch

Implemented REINFORCE, DDPG, TD3, SAC, and PPO from scratch on CartPole and continuous control benchmarks. Worked through derivations of policy gradient theorems and trajectory probability before implementation.
Policy GradientActor-CriticPyTorch
006
Independent · Tooling

Custom Calendar Tracker

Self-contained interactive calendar tracker built as a single HTML file with persistent file-based storage. Designed for personal task / project tracking with zero dependencies and offline-first behavior.
HTMLJSLocal Storage
/ 03

Reports & writeups.

/ 04

Stack & coursework.

Computer Vision
  • OpenCV (C++ / Python)
  • YOLO, SIFT, Gabor filters
  • Camera calibration & AR
  • Multi-object tracking
  • Vision Transformers
Reinforcement Learning
  • PPO, SAC, TD3, DDPG
  • REINFORCE / Policy gradient
  • Q-learning, SARSA, Dyna-Q
  • MCTS & planning
  • F1TENTH simulator
ML & Deep Learning
  • PyTorch, NumPy, scikit-learn
  • CNN architectures
  • Transformer fine-tuning
  • Kalman / Hungarian algorithms
Languages & Tools
  • Python, C++, JavaScript
  • LaTeX (IEEE / AAAI)
  • Git, Linux, CUDA
  • Google Colab, rclone, aria2c
CS 5180
Reinforcement Learning
CS 5330
Pattern Recognition & CV
CS 5800
Algorithms
CS 5200
Database Management
/ 05

Get in touch.

Have a problem
worth seeing?

I'm open to research collaborations, summer internships, and full-time roles starting Spring 2027 in computer vision, perception, autonomy, and applied ML. The fastest way to reach me is email.

polagoni.m@northeastern.edu