Robot training in virtual environments using Reinforcement Learning techniques

Abstract

In this work, we propose a framework to train a robot in a virtual environment using Reinforcement Learning (RL) techniques and thus facilitating the use of this type of approach in robotics. With our integrated solution for virtual training, it is possible to programmatically change the environment parameters, making it easy to implement domain randomization techniques on-the-fly. We conducted experiments with a TurtleBot 2i in an indoor navigation task with static obstacle avoidance using an RL algorithm called Proximal Policy Optimization (PPO). Our results show that even though the training did not use any real data, the trained model was able to generalize to different virtual environments and real-world scenes.