用随机神经网络增强物理模拟器:平面推和弹跳的案例研究
Augmenting Physical Simulators with Stochastic Neural Networks: Case Study of Planar Pushing and Bouncing
摘要:
具有通用不确定性估计的有效的、可推广的物理仿真器在机器人状态估计、规划和控制中具有广泛的应用。在本文中,我们建立这样一个模拟器的两种情况下,平面推动和球反弹,通过增强分析刚体模拟器与神经网络,学习模型的不确定性作为残差。将符号的、确定性的模拟器与可学习的、随机的神经网络相结合,同时为我们提供了表现力、效率和可推广性。我们的模型在真实的标准基准测试中始终优于纯分析和纯学习的模拟器。与使用高斯过程建模不确定性的方法相比,我们的模型运行速度更快,更好地推广到新的对象形状,并且能够表征对象轨迹的复杂分布。
英文摘要:
An efficient, generalizable physical simulator with universal uncertainty estimates has wide applications in robot state estimation, planning, and control. In this paper, we build such a simulator for two scenarios, planar pushing and ball bouncing, by augmenting an analytical rigid-body simulator with a neural network that learns to model uncertainty as residuals. Combining symbolic, deterministic simulators with learnable, stochastic neural nets provides us with expressiveness, efficiency, and generalizability simultaneously. Our model outperforms both purely analytical and purely learned simulators consistently on real, standard benchmarks. Compared with methods that model uncertainty using Gaussian processes, our model runs much faster, generalizes better to new object shapes, and is able to characterize the complex distribution of object trajectories.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。