DeepSim: A Reinforcement Learning Environment Build Toolkit for ROS and Gazebo
This toolkit addresses the challenge for machine learning researchers in accessing robotics domains, though it is incremental as it builds on existing simulation platforms.
The authors tackled the problem of bridging robotics and machine learning by developing DeepSim, a toolkit that enables researchers to create custom reinforcement learning tasks in ROS and Gazebo simulations, resulting in a tool that provides building blocks like collision detection and domain randomization.
We propose DeepSim, a reinforcement learning environment build toolkit for ROS and Gazebo. It allows machine learning or reinforcement learning researchers to access the robotics domain and create complex and challenging custom tasks in ROS and Gazebo simulation environments. This toolkit provides building blocks of advanced features such as collision detection, behaviour control, domain randomization, spawner, and many more. DeepSim is designed to reduce the boundary between robotics and machine learning communities by providing Python interface. In this paper, we discuss the components and design decisions of DeepSim Toolkit.