Understanding the dynamics of unknown object is crucial for collaborative robots including humanoids to more safely and accurately interact with humans. Most relevant literature leverage a force/torque sensor, prior knowledge of object, vision system, and a long-horizon trajectory which are often impractical. Moreover, these methods often entail solving non-linear optimization problem, sometimes yielding physically inconsistent results. In this work, we propose a fast learningbased inertial parameter estimation as more practical manner. We acquire a reliable dataset in a high-fidelity simulation and train a time-series data-driven regression model (e.g., LSTM) to estimate the inertial parameter of unknown objects. We also introduce a novel sim-to-real adaptation method combining Robot System Identification and Gaussian Processes to directly transfer the trained model to real-world application. We demonstrate our method with a 4-DOF single manipulator of physical wheeled humanoid robot, SATYRR. Results show that our method can identify the inertial parameters of various unknown objects faster and more accurately than conventional methods.

翻译：理解未知物体的动力学特性对于包括人形机器人在内的协作机器人更安全、更准确地与人类交互至关重要。大多数相关文献依赖力/力矩传感器、物体先验知识、视觉系统以及长时间轨迹规划，这些方法往往不切实际。此外，这些方法通常需要求解非线性优化问题，有时会得到物理不一致的结果。本文提出一种基于学习的快速惯性参数估计方法，作为一种更实用的方式。我们在高保真仿真中获取可靠数据集，并训练时序数据驱动回归模型（如LSTM）以估计未知物体的惯性参数。我们还引入一种结合机器人系统辨识和高斯过程的新型仿真到现实自适应方法，直接将训练好的模型迁移到实际应用。我们在物理轮式人形机器人SATYRR的4自由度单机械臂上验证了该方法。结果表明，相比传统方法，我们的方法能够更快、更准确地识别各种未知物体的惯性参数。