cadrl_ros
ROS package implementing a deep reinforcement learning algorithm for dynamic obstacle avoidance in ground robots.
What is cadrl_ros?
cadrl_ros is a ROS package that implements a dynamic obstacle avoidance algorithm for ground robots using deep reinforcement learning. It enables robots to navigate safely among moving agents by leveraging a trained neural network policy to make real-time collision avoidance decisions. The package is designed to integrate with robotic perception and control systems, providing a modular solution for autonomous navigation in dynamic environments.
Robotics researchers and engineers working on autonomous ground robots, particularly those focused on motion planning, collision avoidance, and reinforcement learning applications in ROS-based systems.
It offers a proven, research-backed deep RL policy for collision avoidance that has been tested on real hardware, along with datasets and tools for easy experimentation and integration compared to traditional planning methods.
Overview
ROS package for dynamic obstacle avoidance for ground robots trained with deep RL
Use Cases
Best For
- Implementing deep reinforcement learning for robot collision avoidance
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
