top of page

Projects

Course Registration System: Backend Development with Java Spring Boot

Personal Project

  • Created a Java Spring Boot back-end for course registration system, integrating PostgreSQL for database management.

​

  • Tested with 500+ students and courses.

​

  • Implemented authentication and role-based access control, enabling admins to manage courses and students securely.

​

  • Future Scope: Integrating front-end for enhanced user experience.

​

Skills: REST API, Java, Spring Boot, PostgreSQL.

Interactive Tic-Tac-Toe

Course Project

  • Playing Tic-Tac-Toe in a simulated MATLAB environment using a KUKA 7DOF Robotic Manipulator. 

​

  • The robot uses a 3rd Path Order Joint Space Trajectory. 

​

  • The players take turns to input which shelf they choose. Then the robot picks their corresponding box and puts it on that shelf.

​

  • This project is meant to show the use of a KUKA manipulator as a pick-and-place robot. 

Design Image.jpg

Integrating Reconfigurable Foot Design, Multi-modal Contact Sensing, and Terrain Classification for Bipedal Locomotion

Graduate Student Researcher

  • Advisor: Dr. Ye Zhao; Team Lead: Ted Tyler

  • Led a team of 18 people to design and build a sensor-integrated (5 sensors) robotic foot that classifies the terrain that the robot is walking on thereby optimizing the robot’s gait, and improving stability.

  • Finite Element Analysis of weak point on foot that fails due to fatigue.

  • Trained multiple Machine Learning and neural network models for classification of terrain (99% accuracy).

  • Generated CAD models and fabricated the different components, designed a modular terrain bed for testing.

  • Spearheaded the production of a new, in-house & more robust tactile sensor.

  • Signal processing (FFT, Kalman Filters, etc) for IMU Slipping Detection, and Capacitive and Acoustic Sessor data.

  •  Designed a Gelsight Sensor for Pressure Sensor detection based on an MIT sensor.

Screenshot 2023-05-16 at 1.12.40 PM.png

TurtleBot3 path follower

Course Project

  • Assembled the Turtlebot3 Robot.

​

  • Final goal was to create a turtlebot3 path planner that uses OpenCV and SVM to recognise the â€‹signs and move accordingly.

​​

  • It has the ability to avoid obstacles and plans the shortest path to Goal as to avoid any obstructions.

​

  • It can also be commanded via rViz where you would need to click on a point on a map and the TurtleBot will go there in the physical world while avoiding obstacles.

​

  • It uses raspberry Pi 3 b+ and utilises ROS2 Foxy framework.​

Screenshot 2022-12-15 at 2.12.10 PM.png

Human Balance Augmentation

Graduate Student Researcher

  • A project in the EPIC Lab under Dr. Aaron Young. My team lead was Jennifer Leestma.

​​

  • The project’s overarching goal is to develop an intelligent 2-DOF robotic hip exoskeleton to augment biomechanical stability during walking.

 

  • Designing and testing the new 2-degree-of-freedom hip exoskeleton that will be used to study balance augmentation.

 

  • Roles: Preparing the exoskeleton hardware and software for real-time use (3D-CAD & PCB Design), development of control algorithms and machine learning models for the exoskeleton, analysis of biomechanical data, assisting in pilot testing and formal human subjects experiments.

IMG_6557-2.png

Telepresence Robot - Sheldon

Team member (4 people)

  • A Telepresence Robot with Audio/Video Device for communication.

​​

  • Attached with a Robotic Arm for physical interaction with the environment.
     

  • Robot controllable through a website with button controls.
     

  • Arm controllable through hand gesture recognition using MediaPipe ML Algorithm.

​

  • Roles: Hardware assembly of the whole robot. CAD designing of the Robotic Arm. Coding for Raspberry Pi, and Arduino and integration of Website with the hardware.

Screenshot 2022-12-14 at 7.05.03 PM.png

Quadruped Crawler

Personal Project

  • Creation of 8 DOF (Degree of Freedom) Spider robot using Raspberry Pi and PCA9685 controller.

​

  • The robot is controlled by hand gestures and/or a web interface.

​

  • Uses YOLO CNN algorithm (98% accuracy) to recognise hand gestures.

​

  • Utilises ROS1 Platform.

​

  • The web Interface has a joystick style controller and communicates with the robot using Google Firebase.

​

Screenshot 2022-12-15 at 12.41.59 PM.png

Entracer (COVID-19 Contact Tracing)

Team Leader (4 people)

  • As a Part of the ENTRACER team I developed a system consisting of sensors (Melexius for Temperature, Oximeter sensor for oxygen saturation measuring, Barcode Reader for Scanning ID Card for Roll no.)

 

  • We placed it in self designed Box and used it to check the above parameters for visitors at Thapar campus, those in risk zone, had their ID shared on ThingSpeak (IoT platform) from where the data was shared to an app made on flutter and pyre-base.

 

  •  Role:  designing the Box in 3D CAD using Solidworks and Embedding the sensors and the Controller (Raspberry Pi) to it and programming each sensor respectively. 

Screenshot 2022-12-15 at 12.48.27 PM.png

Drone - Quadroter

Personal Project

  • ​I made a Drone with Arduino as its flight controller. 

​

  • The drone was made from scratch from F45 quadcopter design. The code for flight controller was written in its entirety by me. 

​

  • Next phase of this project was to replace the Arduino flight controller with PixHawk and use a raspberry Pi for autonomous control.

​

  • The final raspberry Pi drone can recognise a person's hand gestures using YOLO CNN and move accordingly. 

Screenshot 2022-12-15 at 12.53.55 PM.png

Modification of a Mangonel Model for better design

 

Course Project - 4 people team

  • Understanding the Mangonel Model and modifying it by using a Catapult based throwing mechanism, increasing the throwing range from 30mts to 90mts.
     

  • Adding the functionality of measuring the angular velocity of the throw, by using 2 IR sensors and an Arduino at the stands of the model

 
Screenshot 2022-12-15 at 1.16.11 PM.png

Harry Potter Invisibility Cloak

Personal Project

  • I used OpenCV to create a basic background subtracter that emulates how the invisibility cloak was made in the Harry Potter Movies.

​

  • The code captures the background the moment it starts. 

​

  • After that a mask is created for the cooler of the cloak (the original color).

​​

  • Using bitwise operators foreground and background are created which are then combined to create the illusion that the cloak is invisible.

Screenshot 2022-12-15 at 1.20.33 PM.png
bottom of page