基于物理传感器观测的接地图形网络模拟器
Grounding Graph Network Simulators using Physical Sensor Observations
摘要:
精确模拟现实的物理仿真对于许多工程学科至关重要,例如机械工程和机器人运动规划。近年来,学习图网络仿真器产生了精确的基于网格的仿真,同时只需要传统仿真器的一小部分计算成本。然而,所得到的预测器仅限于从现有的基于网格的模拟器生成的数据中学习,因此不能包括真实世界的感官信息,如点云数据。由于这些预测器必须仅从初始状态模拟复杂的物理系统,因此它们在长期预测中表现出较高的误差累积。在这项工作中,我们将感官信息整合到真实世界观察的地面图形网络模拟器中。特别地,我们利用点云数据预测可变形物体的网格状态。由此产生的模型允许在较长的时间范围内进行准确的预测,即使在模拟中存在不确定性,例如未知的材料特性。由于点云通常不适用于每个时间步长,特别是在在线设置中,因此我们采用基于估算的模型。该模型可以利用这些额外的信息,只有当提供,并诉诸于一个标准的图形网络模拟器,否则。我们通过实验验证了我们的方法对一套基于网格的软体和刚体之间的相互作用的预测任务。我们的方法可以利用额外的点云信息来准确预测现有图形网络模拟器失败的稳定模拟。
英文摘要:
Physical simulations that accurately model reality are crucial for many engineering disciplines such as mechanical engineering and robotic motion planning. In recent years, learned Graph Network Simulators produced accurate mesh-based simulations while requiring only a fraction of the computational cost of traditional simulators. Yet, the resulting predictors are confined to learning from data generated by existing mesh-based simulators and thus cannot include real world sensory information such as point cloud data. As these predictors have to simulate complex physical systems from only an initial state, they exhibit a high error accumulation for long-term predictions. In this work, we integrate sensory information to ground Graph Network Simulators on real world observations. In particular, we predict the mesh state of deformable objects by utilizing point cloud data. The resulting model allows for accurate predictions over longer time horizons, even under uncertainties in the simulation, such as unknown material properties. Since point clouds are usually not available for every time step, especially in online settings, we employ an imputation-based model. The model can make use of such additional information only when provided, and resorts to a standard Graph Network Simulator, otherwise. We experimentally validate our approach on a suite of prediction tasks for mesh-based interactions between soft and rigid bodies. Our method results in utilization of additional point cloud information to accurately predict stable simulations where existing Graph Network Simulators fail.
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。