reiniscimurs/DRL-robot-navigation
Deep Reinforcement Learning for mobile robot navigation in ROS Gazebo simulator. Using Twin Delayed Deep Deterministic Policy Gradient (TD3) neural network, a robot learns to navigate to a random goal point in a simulated environment while avoiding obstacles.
Integrates PyTorch for neural network training with ROS Noetic and Gazebo, using simulated 3D Velodyne lidar data (laser scan) and polar coordinate goal representations as agent inputs. Includes TensorBoard logging for training visualization and supports both native ROS environments and containerized Docker training in headless mode. The implementation has been validated in peer-reviewed research (IEEE RA-L/ICRA 2022) focusing on goal-driven autonomous exploration.
1,262 stars.
Stars
1,262
Forks
189
Language
Python
License
MIT
Category
Last pushed
Dec 13, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/reiniscimurs/DRL-robot-navigation"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
LucasAlegre/sumo-rl
Reinforcement Learning environments for Traffic Signal Control with SUMO. Compatible with...
hilo-mpc/hilo-mpc
HILO-MPC is a Python toolbox for easy, flexible and fast development of...
kyegomez/RoboCAT
Implementation of Deepmind's RoboCat: "Self-Improving Foundation Agent for Robotic Manipulation"...
cbfinn/gps
Guided Policy Search
OpenQuadruped/spot_mini_mini
Dynamics and Domain Randomized Gait Modulation with Bezier Curves for Sim-to-Real Legged Locomotion.