Bridging the Sim-to-Real Gap with Bayesian Inference

TL;DR

This paper introduces SIM-FSVGD, a Bayesian inference method that uses low-fidelity simulators as priors to learn accurate and uncertainty-aware robot dynamics, effectively bridging the sim-to-real gap and enabling efficient model-based control.

Contribution

The paper proposes SIM-FSVGD, a novel approach combining Bayesian inference with physical priors to improve robot dynamics learning from limited data.

Findings

Accurate mean model estimation and uncertainty quantification achieved.

Effective bridging of the sim-to-real gap demonstrated on a high-performance RC car.

Successful model-based RL for dynamic parking with less data than previous methods.

Abstract

We present SIM-FSVGD for learning robot dynamics from data. As opposed to traditional methods, SIM-FSVGD leverages low-fidelity physical priors, e.g., in the form of simulators, to regularize the training of neural network models. While learning accurate dynamics already in the low data regime, SIM-FSVGD scales and excels also when more data is available. We empirically show that learning with implicit physical priors results in accurate mean model estimation as well as precise uncertainty quantification. We demonstrate the effectiveness of SIM-FSVGD in bridging the sim-to-real gap on a high-performance RC racecar system. Using model-based RL, we demonstrate a highly dynamic parking maneuver with drifting, using less than half the data compared to the state of the art.