zerosansan/dqn_qlearning_sarsa_mobile_robot_navigation

A Reinforcement Learning (RL) based navigation implementation for mobile robot navigation. Q-Learning, SARSA and Deep Q-Network algorithms were compared.

25
/ 100
Experimental

This helps robotics researchers and engineers train mobile robots to navigate autonomously using reinforcement learning. You can input various learning algorithms (Q-Learning, SARSA, DQN) and simulated or real-world sensor data from a Turtlebot3 robot. The output is a trained robot capable of independent navigation within an environment. This is for professionals working on autonomous robot development.

No commits in the last 6 months.

Use this if you are developing or experimenting with mobile robot navigation strategies and want to compare different reinforcement learning approaches in simulation and on a physical robot.

Not ideal if you need to control non-Turtlebot3 robot platforms or are looking for ready-to-deploy, off-the-shelf navigation solutions without customization.

robot-navigation autonomous-systems robotics-research mobile-robot-development
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 10 / 25

How are scores calculated?

Stars

40

Forks

4

Language

Python

License

Last pushed

Sep 25, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/zerosansan/dqn_qlearning_sarsa_mobile_robot_navigation"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.