John-Wendell/DDPG-AirSim-Drone-Obstacle-Avoidance
Using DDPG and ConvLSTM to control a drone to avoid obstacle in AirSim
This project helps drone researchers and robotics engineers develop and test autonomous drone navigation systems, specifically for obstacle avoidance in the vertical direction. It takes simulated depth camera images and height data as input and produces precise height control instructions for the drone. The output is a drone capable of navigating environments without colliding with obstacles above or below it.
Use this if you are a robotics researcher or drone developer working on improving autonomous drone navigation and obstacle avoidance in simulated environments like AirSim.
Not ideal if you need a production-ready solution for real-world drone deployment, as this is a research-oriented project developed for a course with potential bugs and no fine-tuning.
Stars
61
Forks
5
Language
Python
License
MIT
Category
Last pushed
Nov 03, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/John-Wendell/DDPG-AirSim-Drone-Obstacle-Avoidance"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
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...
reiniscimurs/DRL-robot-navigation
Deep Reinforcement Learning for mobile robot navigation in ROS Gazebo simulator. Using Twin...
kyegomez/RoboCAT
Implementation of Deepmind's RoboCat: "Self-Improving Foundation Agent for Robotic Manipulation"...
cbfinn/gps
Guided Policy Search