🤖 trpy — Python Interface for Trossen Robotic Arms

Type: Open-source Robotics Library

Category: Robot Control / HRI / Prototyping

Overview

Lightweight Python library for controlling Trossen robotic arms via CLI and scripts, designed for rapid experimentation without requiring full ROS2 setup.

Impact

• Enabled faster prototyping for Human-Robot Interaction (HRI) research
• Lowered barrier for students unfamiliar with ROS2
• Supported multi-arm control in research workflows

Key Features

• Record & playback motion sequences
• Auto-homing routines
• Motion smoothing filters
• Asynchronous control for multiple arms

My Contribution

• Designed and implemented full library architecture
• Built async control system for multi-arm setups
• Integrated usability-focused CLI for rapid testing

Tech: Python, Robotics Control, Async Systems

• 🔗 GitHub

🚗 Universal Mobile Robot Platform

Type: Robotics Platform / Applied AI System

Category: Mobile Robotics / HRI / Autonomous Systems

Overview

Built a cost-effective mobile robot platform capable of carrying heavy payloads and operating in real-world indoor environments for research and prototyping.

Impact

• Designed for 100 kg payload capacity
• Achieves ~2 m/s speed on a 10° incline
• Currently being adapted for AI-driven autonomous tasks at Adobe Makerspace

Real-World Usage

Used internally at Adobe Makerspace to prototype AI-powered robotics workflows.

• Being extended to integrate models like Claude for:
  • Autonomous navigation
  • Office assistance (guidance, task automation)

My Contribution

• Built the original robot platform (hardware + system design)
• Provided architecture + codebase for further development
• Enabled transition from research prototype → internal AI robotics platform

System Design

• Dual 350W motors
• High-strength frame (wood/aluminum variants)
• Modular design for future autonomy upgrades

Collaboration Note

Initial follow-on development at Adobe was led by another engineer. I contributed the platform, architecture, and foundational system.

• 🔗 GitHub
• 🔗 Project site

🦿 WaltZ — Bipedal Walking Robot

Type: University Robotics Club / Education Platform

Category: Bipedal Locomotion / Embedded Control / HRI Teaching

Overview

A flagship initiative by the Khoury Robotics Club, WaltZ is a 6-DoF bipedal robot driven by an RP2040 microcontroller and 9-axis IMU. Built to be affordable and easy to fabricate, this ongoing project serves as an educational tool in robotics courses, showcasing core principles of gait, balance, and embedded control.

Impact

• Low-cost, fabricable platform lowers the barrier to hands-on bipedal robotics
• Designed for use in coursework on gait, balance, and real-time control
• Ongoing build—intended to grow with future navigation and HRI modules

Key Features

• 6-DoF leg architecture
• RP2040-based embedded control
• 9-axis IMU for orientation and balance experiments

Context

Developed within the Khoury Robotics Club as a shared club initiative; I contribute to mechanical integration, embedded software, and documentation alongside other members.

Tech: RP2040, Embedded C/C++, IMU, CAD & fabrication

• 🔗 GitHub

🎯 SHAPER — Spatially Handling Arm Projectile Evader

Type: Simulation / Research Project

Category: Evolutionary Algorithms / Robotics Simulation

Overview

A simulated robotic arm learns to evade incoming projectiles using a custom genetic algorithm. The entire stack is built with NumPy and Pygame only—no external ML frameworks—so the focus stays on algorithm design and efficient training dynamics.

Impact

• Multi-stage scoring gradually increases difficulty, substantially speeding up convergence versus naive training
• Demonstrates staged curriculum learning without deep learning dependencies
• Reproducible, lightweight codebase suitable for coursework and experimentation

Key Features

• Custom genetic algorithm for policy search
• Multi-stage scoring function with incremental task difficulty
• 2D simulation with NumPy + Pygame only

My Contribution

• Designed and implemented the full simulation and training pipeline
• Authored the technical report documenting methodology and results

Tech: Python, NumPy, Pygame

• 🔗 GitHub
• 🔗 Video
• 🔗 Report (PDF)

🚌 MBTA Bus Tracker

Type: Web Application

Category: Transit / Real-time Data / Maps

Overview

A web-based platform for real-time tracking of MBTA-operated buses. It emphasizes route-based visualization and live vehicle positions so riders and planners can see what is on the road without digging through raw feeds.

Impact

• Makes MBTA bus activity easier to interpret for daily commuting decisions
• Supports route-level situational awareness for transit management and enthusiasts
• Continuously updated as APIs and routes evolve

Key Features

• Route-centric map and list views
• Dynamic location updates from MBTA real-time data
• Responsive layout for desktop and mobile browsers

My Contribution

• End-to-end product: UX, frontend implementation, and deployment
• Integration with MBTA APIs and ongoing maintenance

Tech: Web stack, MBTA real-time APIs, mapping & visualization

• 🔗 Live demo
• 🔗 GitHub