arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.05456cs.ROcs.LGcs.SYeess.SY
收藏

学习滑动未知物体与微分物理模拟

Learning to Slide Unknown Objects with Differentiable Physics Simulations

Rutgers University(罗格斯大学)

Changkyu Song, Abdeslam Boularias

摘要:

我们提出了一种新的技术,推动一个未知的对象从一个初始配置的目标配置与稳定性约束。所提出的方法利用可微物理模型的最新进展来学习被推物体的未知机械特性,例如它们的质量分布和摩擦系数。所提出的学习技术计算物体的预测姿态与其实际观察到的姿态之间的距离的梯度,并利用该梯度来搜索减小现实差距的机械特性的值。所提出的方法还用于优化策略,以有效地将对象推向所需的目标配置。使用真实机器人采集数据的真实物体实验表明,该方法可以从少量的推动动作中识别异构物体的力学特性。

英文摘要:

We propose a new technique for pushing an unknown object from an initial configuration to a goal configuration with stability constraints. The proposed method leverages recent progress in differentiable physics models to learn unknown mechanical properties of pushed objects, such as their distributions of mass and coefficients of friction. The proposed learning technique computes the gradient of the distance between predicted poses of objects and their actual observed poses and utilizes that gradient to search for values of the mechanical properties that reduce the reality gap. The proposed approach is also utilized to optimize a policy to efficiently push an object toward the desired goal configuration. Experiments with real objects using a real robot to gather data show that the proposed approach can identify the mechanical properties of heterogeneous objects from a small number of pushing actions.

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。

↑