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.

翻译：我们提出SIM-FSVGD方法用于从数据中学习机器人动力学。与传统方法不同，SIM-FSVGD利用低保真度物理先验（例如以仿真器形式）来正则化神经网络模型的训练。该方法不仅能在低数据量下学习精确动力学，当数据更充裕时仍能保持扩展性与优越性能。实验表明，隐式物理先验学习可同时实现准确的均值模型估计与精确的不确定性量化。我们通过高性能RC赛车系统验证了SIM-FSVGD在弥合仿真与现实差距方面的有效性。基于模型强化学习方法，我们成功演示了包含漂移行为的高动态泊车操作，且所需数据量不到现有最优方法的半数。