S.T.E.W.A.R.D: Smart TErrestrial WArehouse Robot Deployment

Made during the e-yantra Robotics Competition 2020-21, Sahayak Bot was the first project that introduced me to simulation-based advanced robotics development using ROS & Gazebo. We focused on the developement of the autonomy stack of Sahayak Bot, a mobile manipulator, including navigation, SLAM, perception, manipulation & mission planning using ROS, Gazebo and Moveit!. Upon completition our implementation was selected among top 7 finalists out of almost 500 teams.

Our in-house custom designed and fabricated AMR at A.T.O.M. The hardware and software design follows a modular architecture making this fitting for the multiple applications, hence the name MR (ModulaR) Robot.

The first project I made in college that got me into Computer Vision and Machine Learning. By tracking the end of a retroreflector-tipped harry potter wand replica and training my own SVM for handwritten character recognition, I was able to do magic in real life. This was demostrated by the spell Alohomora that opens a box when you write ‘A’ in mid-air using the wand. The project got featured in official blogs at Raspberry Pi, Hackaday and a complete article in the 86th issue of MagPi, the official Raspberry Pi magazine

Built a fleet of two line-following robots with custom 3D-printed pick-and-place mechanisms during the e-Yantra Robotics Competition 2021–22. Developed algorithms for grid-based path planning, mapping, fleet management, PID-based line following and manipulation in Elixir. Selected among the top 5 teams out of nearly 300.

Showcased my internship project at Technoyantra, one of the early open-source demonstrations integrating ROS 2, Nav2, SLAM Toolbox, and Ignition Gazebo for the in-house AMR, IGT.

Showcased our project for the NASA SpaceROS Summer Sprint Challenge 2024, featuring custom Gazebo plugins for extraterrestrial simulations.

Showcased my internship project at Acceleration Robotics India about developing custom plugins and 3D models for open world outdoor simulations in Gazebo

An open source project being developed as part of A.T.O.M Robotics Lab. The project is intended to work as a one-stop solution for easily deploying perception pipelines with common applications like object detection, image segmentation, image pre processing, etc. The project follows modular plugin-based architecture much like Nav2 in concept. The project is actively used in A.T.O.M’s in-house mobile robot - MR Robot

Presented my GSoC’23 project, “Automatic Computation of Moments of Inertia of SDFormat Links,” with the Gazebo team at Open Robotics