SimPRIVE: a Simulation framework for Physical Robot Interaction with Virtual Environments
This work addresses the problem of safely and cost-effectively testing machine learning algorithms in cyber-physical systems for robotics researchers and engineers, though it is incremental as it builds on existing simulation and ROS technologies.
The paper introduces SimPRIVE, a simulation framework that enables physical robots to interact with virtual environments, allowing testing of complex algorithms like reinforcement learning for obstacle avoidance on a real rover in a virtual office setting, with the physical rover successfully navigating without collisions in a limited indoor space using a LiDAR-based heuristic.
The use of machine learning in cyber-physical systems has attracted the interest of both industry and academia. However, no general solution has yet been found against the unpredictable behavior of neural networks and reinforcement learning agents. Nevertheless, the improvements of photo-realistic simulators have paved the way towards extensive testing of complex algorithms in different virtual scenarios, which would be expensive and dangerous to implement in the real world. This paper presents SimPRIVE, a simulation framework for physical robot interaction with virtual environments, which operates as a vehicle-in-the-loop platform, rendering a virtual world while operating the vehicle in the real world. Using SimPRIVE, any physical mobile robot running on ROS 2 can easily be configured to move its digital twin in a virtual world built with the Unreal Engine 5 graphic engine, which can be populated with objects, people, or other vehicles with programmable behavior. SimPRIVE has been designed to accommodate custom or pre-built virtual worlds while being light-weight to contain execution times and allow fast rendering. Its main advantage lies in the possibility of testing complex algorithms on the full software and hardware stack while minimizing the risks and costs of a test campaign. The framework has been validated by testing a reinforcement learning agent trained for obstacle avoidance on an AgileX Scout Mini rover that navigates a virtual office environment where everyday objects and people are placed as obstacles. The physical rover moves with no collision in an indoor limited space, thanks to a LiDAR-based heuristic.