A Framework for Learning Predator-prey Agents from Simulation to Real World
This provides a practical tool for robotics researchers working on evolutionary algorithms in predator-prey tasks, though it is incremental in combining existing components.
The paper tackles the problem of transferring learned behaviors from simulation to real-world predator-prey robot systems by proposing a framework that integrates OpenAI Gym, ROS, and Gazebo, with results including successful co-evolution of predators and prey using NEAT and published source code.
In this paper, we propose an evolutionary predatorprey robot system which can be generally implemented from simulation to the real world. We design the closed-loop robot system with camera and infrared sensors as inputs of controller. Both the predators and prey are co-evolved by NeuroEvolution of Augmenting Topologies (NEAT) to learn the expected behaviours. We design a framework that integrate Gym of OpenAI, Robot Operating System (ROS), Gazebo. In such a framework, users only need to focus on algorithms without being worried about the detail of manipulating robots in both simulation and the real world. Combining simulations, real-world evolution, and robustness analysis, it can be applied to develop the solutions for the predator-prey tasks. For the convenience of users, the source code and videos of the simulated and real world are published on Github.