Tennis AI

Description

Training robots to play sports can be a challenging task. Here in this implementation, we trained Reinforcement Learning agents to play tennis. With the help of this implementation, we have a proof of concept model and architecture that can help an agent play tennis.

This simulation can then be used for the real-time implementation of robots that can play tennis. Such robots will have a lot of importance as they can assists sports players in their training, play with kids, etc. Due to the COVID-19 pandemic as kids are not able to play with each other these robots can become their buddies and play with them.

Files

Report.md

md - 4.09 kB - 06/18/2021 at 02:03

Download

README.md

md - 2.05 kB - 06/18/2021 at 02:03

Download

1411_256_256_critic.pth

pth - 286.90 kB - 06/18/2021 at 02:03

Download

1411_256_256_actor.pth

pth - 294.87 kB - 06/18/2021 at 02:03

Download

1039_96_96_critic.pth

pth - 48.76 kB - 06/18/2021 at 02:03

Download

Components

1 × Mouse

1 × Keyboard Development Kits, Boards and Systems / Development Kits and Boards

1 × Panda PAU05 WiFi Adapter The Jetson nano does not have a Wi-Fi interface

1 × 32 GB SD card

1 × 5v Power Supply (Barrel Jack Type)

Project Logs

Collapse

Testing 2
srimanthtenneti • 06/28/2021 at 15:18 • 0 comments

Completed testing the Critic-Network and tuning
Testing 1
srimanthtenneti • 06/28/2021 at 15:17 • 0 comments

Completed initial actor-network testing and tuning
Completion log
srimanthtenneti • 06/18/2021 at 02:48 • 0 comments

1. Finished defining the Actor and Critic models design.

2. Completed the DDPG implementation with the OU noise process and a replay buffer.

3. Finished setting up the soft-target updates for the agents

4. Completed and successfully trained the RL agents.

5. Completed the software documentation.
Completion log
srimanthtenneti • 06/18/2021 at 02:11 • 0 comments

1. Finished defining the Actor and Critic models design.
2. Completed the DDPG implementation with the OU noise process and a replay buffer.
3. Finished setting up the soft-target updates for the agents
4. Completed and successfully trained the RL agents.
5. Completed the software documentation.

View all 4 project logs

Build Instructions

Collapse

Setup Instructions

1. Download and setup Unity ML agents

2. Install Anaconda and Pytorch

3. Run the ipynb notebook.

Discussions

Edward Sanders wrote 03/19/2023 at 07:46

As technology continues to improve, the possibility of a robot that plays tennis becomes more and more of a reality. The creation of a robot that can play tennis at a competitive level would revolutionize the sport by providing a new level of competition and challenge for players. A tennis-playing robot would have to be equipped with advanced sensors and cameras to pick up on the ball's speed, trajectory, and spin, and artificial intelligence algorithms to respond to the ball's movement. I found these extra resources very useful for gaining more information about the tennis department in the colleges.

Are you sure? yes | no

Tennis AI

Become a Hackaday.io member

Just one more thing

Description

Files

Report.md

README.md

1411_256_256_critic.pth

1411_256_256_actor.pth

1039_96_96_critic.pth

Components

Project Logs Collapse

Testing 2

Testing 1

Completion log

Completion log

Build Instructions Collapse

Enjoy this project?

Discussions

Become a Hackaday.io Member

Does this project spark your interest?

Report project as inappropriate

Send message

Remove Member

Project Logs

Collapse

Build Instructions

Collapse