A data-driven large-scale optimization approach for task-specific physics realism in real-time robotics simulation

Andreas Bihlmaier, Kai Kohlhoff

Abstract: Physics-based simulation of robots requires models of the simulated robots and their environment. For a realistic simulation behavior, these models must be accurate. Their physical properties such as geometric and kinematic values, as well as dynamic parameters such as mass, inertia matrix and friction, must be modelled. Unfortunately, this problem is hard for at least two reasons. First, physics engines designed for simulation of rigid bodies in real-time cannot accurately describe many common real world phenomena, e.g. (drive) friction and grasping. Second, the prime candidate solution to the model parameter problem, classical parameter identification algorithms, although well-studied and efficient, often necessitate a significant manual engineering effort and may not be applicable due to application constraints. Thus, we present a data-driven general purpose tool, which allows to optimize model parameters for (task-specific) realistic simulation behavior. Our approach directly uses the simulator and the model under optimization to improve model parameters. The optimization process is highly distributed and uses a hybrid optimization approach based on metaheuristics and the Ceres non-linear least squares solver. The user only has to provide a configuration file that specifies which model parameter to optimize together with realism criteria and a set of reference recordings from the real robot system.