top of page
Can We Save Our Oceans?
Our Work
Robo Daycare Video Presentation
RoboDaycare Demo
Play Video
Back to the Wild
Robot Walking
Robot Walking
Play Video

Walker and Hopper was trained to walk from scratch .

The hopper was trained for 35000 episodes and walker was trained for 15000 episodes.

Governing Polution
Robot Walking in Wind Environment
Play Video
Robot  Walking - Wind  Environment

The agents were trained to walk straight and upright  in a windy environment with the help of transfer learning.

Transfer learning helped in hastening the training of agents in windy environment.

Robot dribbling a ball
Robot Dribbling a Ball
Play Video
Cry Us a River

Transfer learning proved to be effective even for tasks like dribbling a ball.

Robot kicking a ball
Robot Kicking a Ball
Play Video

With proper reward function and transfer learning the agent is able to kick the ball to a considerable distance.

Climate Change, Reversed
Humanoid Kicking a ball 
Humanoid Kicking a ball
Play Video
Bio

Technical Paper

Table of Contents

  • Introduction

  • Prior research

  • Tools and Software Used

  • Results and Analysis

  • Limitations , Conclusion & Future work

Link  to  the paper - https://github.com/csci-599-applied-ml-for-games/Robo-Daycare/blob/master/Technical_Paper.pdf

ROBO DAYCARE TEAM

Name: Anubhab Sen
Email: anubhabs@usc.edu
LinkedIn - https://www.linkedin.com/in/anubhabsen/
Name: Geethika Rasineni
Email: rasineni@usc.edu
LinkedIn - http://linkedin.com/in/geethika-rasineni
Contact
bottom of page