Quick demonstration of a converged policy using ROS2Learn framework and the gym-gazebo2 toolkit. We execute a deterministic run and also use settings that replicate a real behavior of the robot.
The first gym-gazebo was a successful proof of concept, which is being used by multiple research laboratories and many users of the robotics community. Given its positive impact, specially regarding usability, researchers at Acutronic Robotics have now freshly launchedgym-gazebo2.
“This is the logical evolution towards our initial goal: to bring RL methods into robotics at a professional and industrial level.” — Risto Kojcev, head of AI, Acutronic Robotics
The AI team he leads researches on how reinforcement learning (RL) can be used instead of traditional path planning techniques.
“We aim to train behaviors that can be applied in complex dynamic environments, which resemble the new demands of agile production and human robot collaboration scenarios.”
Achieving this would lead to faster and easier development of robotic applications and moving the RL techniques from a research setting to a production environment. gym-gazebo2 is a step forward in this long-term goal.
The paper, which is available here, presents an upgraded, real-world, application-oriented version of gym-gazebo, the ROS- and Gazebo-based RL toolkit, which complies with OpenAI’s Gym.