SoheilKhatibi/Humanoid-Robot-Active-Vision-DDQN
The code release of "Real-time Active Vision for a Humanoid Soccer Robot Using Deep Reinforcement Learning" paper, ICAART 2021
This project helps roboticists develop and test vision systems for humanoid robots in a simulated soccer environment. It takes simulated sensor data from a RoboCup-like environment and outputs optimized gaze control strategies, enabling the robot to track the ball and other objects more effectively. It's designed for researchers and engineers working on autonomous robot navigation and perception.
No commits in the last 6 months.
Use this if you are researching active vision systems for humanoid robots in a simulated competitive setting and need to train robots to intelligently control their gaze.
Not ideal if you are looking for a pre-trained, production-ready vision system for a physical robot or a general-purpose object recognition tool.
Stars
9
Forks
—
Language
C++
License
—
Category
Last pushed
Mar 29, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/SoheilKhatibi/Humanoid-Robot-Active-Vision-DDQN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.