Implicit Kinematic Policies:在端到端机器人学习中统一关节和笛卡尔动作空间
Implicit Kinematic Policies: Unifying Joint and Cartesian Action Spaces in End-to-End Robot Learning
摘要:
动作表示是深度网络端到端机器人学习中一个重要但经常被忽视的方面。选择一个动作空间而不是另一个动作空间(例如,目标关节位置或笛卡尔末端执行器姿势)可能会导致各种下游任务之间惊人的明显性能差异-因此,大量研究一直致力于为给定应用找到正确的动作空间。然而,在这项工作中,我们反而研究了我们的模型如何发现和学习使用哪个动作空间。利用最近关于隐式行为克隆的工作,将观察和动作作为输入,我们证明了可以在多个不同的空间中向同一策略呈现相同的动作-允许它从每个空间学习归纳模式。具体来说,我们研究的好处相结合的笛卡尔和联合行动空间的背景下,学习操作技能。为此,我们提出了隐式运动策略(IKP),它将运动链作为深度网络中的可微模块。几个模拟连续控制任务的定量实验-从铲起成堆的小物体,到用肘部举箱子,再到用校准错误的机器人精确插入块-表明IKP不仅比基线替代品更好地从像素中学习复杂的可伸缩和非可伸缩操作,而且还可以学习补偿小的关节编码器偏移误差。最后,我们还运行一个真正的UR 5e定性实验,以证明我们的算法的可行性,在物理机器人系统与真实数据。有关代码和补充材料,请参见https://tinyurl.com/4wz3nf86。
英文摘要:
Action representation is an important yet often overlooked aspect in end-to-end robot learning with deep networks. Choosing one action space over another (e.g. target joint positions, or Cartesian end-effector poses) can result in surprisingly stark performance differences between various downstream tasks -- and as a result, considerable research has been devoted to finding the right action space for a given application. However, in this work, we instead investigate how our models can discover and learn for themselves which action space to use. Leveraging recent work on implicit behavioral cloning, which takes both observations and actions as input, we demonstrate that it is possible to present the same action in multiple different spaces to the same policy -- allowing it to learn inductive patterns from each space. Specifically, we study the benefits of combining Cartesian and joint action spaces in the context of learning manipulation skills. To this end, we present Implicit Kinematic Policies (IKP), which incorporates the kinematic chain as a differentiable module within the deep network. Quantitative experiments across several simulated continuous control tasks -- from scooping piles of small objects, to lifting boxes with elbows, to precise block insertion with miscalibrated robots -- suggest IKP not only learns complex prehensile and non-prehensile manipulation from pixels better than baseline alternatives, but also can learn to compensate for small joint encoder offset errors. Finally, we also run qualitative experiments on a real UR5e to demonstrate the feasibility of our algorithm on a physical robotic system with real data. See https://tinyurl.com/4wz3nf86 for code and supplementary material.
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。