IITISoC-24-IVR6-RL-based-Control-of-Autonomous-Vehicles

Goal:

To Test and Implement Reinforcement Learning on Real Hardware to take care of the external disturbances in the system automatically.

People Involved :

Mentors:

• K Niketh Reddy
• Giridhar AP

Members:

• Dishank Jaiswal
• Aditya gupta
• Anay Sawant
• Bhavya Shah

Walkthrough

We used Deep Q-Learning to solve the two problems of a Self balancing robot and Ball balancing about an axis on a plane. The self balancing robot folder of the repository contains the simulation urdf which is to be used on a software such as Isaac Sim, or any other, to simulate and make the algorithm work better.

What we learned:

We learned about the Reinforcement Learning and how we can use it to automate things as the agent learns according to a policy over time. We learned about simulation tools such as Gazebo Sim and Isaac Sim/ Gym which are very popular in the world for simulation purposes.