EAGERx: Graph-Based Framework for Sim2real Robot Learning

TL;DR

EAGERx is a versatile, open-source framework that enhances sim2real robot learning by integrating simulation and real-world control, addressing discrepancies through delay simulation, domain randomization, and synchronization.

Contribution

It introduces a unified software pipeline supporting various simulators, enabling effective sim2real transfer with features like delay simulation and domain randomization.

Findings

EAGERx effectively narrows the sim2real gap in robot learning.

It supports diverse robotic systems with consistent simulation behavior.

The framework is open source and adaptable to different simulators.

Abstract

Sim2real, that is, the transfer of learned control policies from simulation to real world, is an area of growing interest in robotics due to its potential to efficiently handle complex tasks. The sim2real approach faces challenges due to mismatches between simulation and reality. These discrepancies arise from inaccuracies in modeling physical phenomena and asynchronous control, among other factors. To this end, we introduce EAGERx, a framework with a unified software pipeline for both real and simulated robot learning. It can support various simulators and aids in integrating state, action and time-scale abstractions to facilitate learning. EAGERx's integrated delay simulation, domain randomization features, and proposed synchronization algorithm contribute to narrowing the sim2real gap. We demonstrate (in the context of robot learning and beyond) the efficacy of EAGERx in accommodating diverse robotic systems and maintaining consistent simulation behavior. EAGERx is open source and its code is available at https://eagerx.readthedocs.io.