Bridging the Sim-to-Real Gap with Bayesian Inference

arXiv:2403.16644v1 Announce Type: cross
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 …

abstract arxiv bayesian bayesian inference cs.lg cs.ro data dynamics fidelity form gap inference low network neural network robot sim training type