Arvind R.

I am an Aerospace Engineer and I am proficient in CAD modelling, Rigid Body Dynamics and Control systems. The tools I am comfortable using include Autodesk inventor, fusion360, Solidworks and Matlab/Simulink Apart from this, I am also proficient in CFD, FEA and thermal analysis using Ansys.

Professional Outline
Academic Background:

UNIVERSITY OF MARYLAND, College Park, MD: M.Eng. Aerospace Engineering

AMRITA SCHOOL OF ENGINEERING, India: B.E. Aerospace Engineering

Certifications:

MIT: Discovering and Implementing Your Leadership Strengths
Certificate ID: ab524e48-c963-4ecc-bd49-9833b0bdf851

MIT: Machine Learning, Modeling, and Simulation Principles
Certificate ID: dc123f7f-1092-4bfb-a820-13ccc62e2a70

Current skills and services:
Python
AutoCAD
Ardupilot/Pixhawk
Stability & Control Systems
C++
Inventor
Raspberry pi
Engineering Simulations
Matlab/Simulink
Fusion360
Arduino
3D Modelling
ROS/ROS2
Solidworks
Nvidia Jetson
Aerodynamics
Linux
Catia
Pytorch/TensorRT
Prototyping
AI tools
Ansys
Deepstream
Vehicle Automation

Professional Experience

AINET | Freelance Aerospace & Robotics Engineer
Engineered and developed advanced eVTOL drone systems and automated ground vehicles by integrating microcontrollers and sensors to achieve autonomous functionality.
Led the design of mission-capable UAVs for Department of Defence RFI/RFP submissions, creating designs that successfully met or exceeded specified flight envelopes and mission goals.
Architected and deployed an advanced machine vision system for guidance and navigation, utilizing a stereo disparity ML model to generate real-time depth maps from custom-built stereo cameras.
Executed comprehensive flight tests on Pixhawk-based UAVs, successfully tuning flight stability parameters and validating advanced guidance and navigation systems.
Developed custom ROS2 drivers and packages in C++ and Python to integrate sensors like rangefinders, LIDARs, and cameras into a unified robotics architecture. Architected and deployed a sophisticated object detection and classification system for autonomous vehicles by training an AI model with NVIDIA TAO and running it on an NVIDIA Jetson computer.