myGym: Modular Toolkit for Visuomotor Robotic Tasks

TL;DR

myGym is a modular virtual robotic toolkit designed for reinforcement learning and visuomotor tasks, enabling easy transfer to real robots, customization, and support for intrinsic motivation and human-robot interaction scenarios.

Contribution

It introduces a flexible, modular simulation environment that supports visuomotor, unsupervised, and collaborative tasks, with pretrained visual modules and easy customization.

Findings

Supports transfer from simulation to real robots

Enables rapid prototyping with pretrained visual modules

Flexible environment for diverse visuomotor tasks

Abstract

We introduce a novel virtual robotic toolkit myGym, developed for reinforcement learning (RL), intrinsic motivation and imitation learning tasks trained in a 3D simulator. The trained tasks can then be easily transferred to real-world robotic scenarios. The modular structure of the simulator enables users to train and validate their algorithms on a large number of scenarios with various robots, environments and tasks. Compared to existing toolkits (e.g. OpenAI Gym, Roboschool) which are suitable for classical RL, myGym is also prepared for visuomotor (combining vision & movement) unsupervised tasks that require intrinsic motivation, i.e. the robots are able to generate their own goals. There are also collaborative scenarios intended for human-robot interaction. The toolkit provides pretrained visual modules for visuomotor tasks allowing rapid prototyping, and, moreover, users can customize the visual submodules and retrain with their own set of objects. In practice, the user selects the desired environment, robot, objects, task and type of reward as simulation parameters, and the training, visualization and testing themselves are handled automatically. The user can thus fully focus on development of the neural network architecture while controlling the behaviour of the environment using predefined parameters.