Robot_gym: accelerated robot training through simulation in the cloud with ROS and Gazebo
This work addresses the challenge of efficient robot training for roboticists, though it appears incremental as it builds on existing simulation tools like ROS and Gazebo.
The paper tackles the problem of high experimentation costs in robot training by introducing robot_gym, a cloud-based simulation framework that accelerates training time by over 33% for simple tasks while maintaining accuracy and repeatability.
Rather than programming, training allows robots to achieve behaviors that generalize better and are capable to respond to real-world needs. However, such training requires a big amount of experimentation which is not always feasible for a physical robot. In this work, we present robot_gym, a framework to accelerate robot training through simulation in the cloud that makes use of roboticists' tools, simplifying the development and deployment processes on real robots. We unveil that, for simple tasks, simple 3DoF robots require more than 140 attempts to learn. For more complex, 6DoF robots, the number of attempts increases to more than 900 for the same task. We demonstrate that our framework, for simple tasks, accelerates the robot training time by more than 33% while maintaining similar levels of accuracy and repeatability.