Robotics Software and Cloud Projects

Robotics

Conduct research on multi-robot long horizon planning using the Monte Carlo Tree Search (MCTS) algorithm to efficiently rearrange objects into complex desired goal locations.
Ensured collision-free navigation for the multiple mobile robots all the while aiming to achieve a highly efficient plan that can produce interesting emerging behaviors for the robots reducing the overall distance travelled.
Skills: Python, PyBullet, Numpy, RRT star, Monte Carlo Tree Search, Cost Based Search Due to ongoing research, I am unable to share the current images and videos of the research. The above images are a simple version of expected results I am working on. Source

This is a course project for the CS 558 Introduction to Robot Learning course where I am trying to move the robot arm to a specified goal configuration using RRT algorithm implemented from scratch.
Here the RRT Tree Nodes are shown in workspace by first converting the points in configuration space to workspace using the forward kinematics equations and plotting the end effector position in workspace.
Skills: Python, PyBullet, Numpy, RRT, Forward Kinematics

Worked on the realtime alerting feature for the WSO2 Choreo applications. This feature enables users to create Out-of-Memory and Log-based alerts for their applications and get notified via email when the alert conditions are met.
This is an event driven architecture where the events are generated by the Azure Functions that are responsible for monitoring the WSO2 Choreo applications and they are sent to the Azure EventHubs.
The Azure Stream Analytics is used to process the events and to trigger the Azure Functions responsible for sending the email notifications.
Co-lead the architecture design and the implementation of the feature from start to finish.
Skills: Python, Azure EventHubs, Azure Stream Analytics, Azure Functions, Azure MSSQL, Azure Log Analytics.