Data_Sheet_1_Learning Transferable Push Manipulation Skills in Novel Contexts.PDF

This paper is concerned with learning transferable forward models for push manipulation that can be applying to novel contexts and how to improve the quality of prediction when critical information is available. We propose to learn a parametric internal model for push interactions that, similar for humans, enables a robot to predict the outcome of a physical interaction even in novel contexts. Given a desired push action, humans are capable to identify where to place their finger on a new object so to produce a predictable motion of the object. We achieve the same behaviour by factorising the learning into two parts. First, we learn a set of local contact models to represent the geometrical relations between the robot pusher, the object, and the environment. Then we learn a set of parametric local motion models to predict how these contacts change throughout a push. The set of contact and motion models represent our internal model. By adjusting the shapes of the distributions over the physical parameters, we modify the internal model's response. Uniform distributions yield to coarse estimates when no information is available about the novel context. We call this an unbiased predictor. A more accurate predictor can be learned for a specific environment/object pair (e.g., low friction/high mass), called a biased predictor. The effectiveness of our approach is demonstrated in a simulated environment in which a Pioneer 3-DX robot equipped with a bumper needs to predict a push outcome for an object in a novel context, and we support those results with a proof of concept on a real robot. We train on two objects (a cube and a cylinder) for a total of 24,000 pushes in various conditions, and test on six objects encompassing a variety of shapes, sizes, and physical parameters for a total of 14,400 predicted push outcomes. Our experimental results show that both biased and unbiased predictors can reliably produce predictions in line with the outcomes of a carefully tuned physics simulator.

本研究聚焦于可迁移的推送操控（push manipulation）前向模型学习，该模型能够适配全新场景，并探索当关键信息可用时如何提升预测质量。我们提出为推送交互构建参数化内部模型，该模型与人类的推理逻辑类似，可使机器人即使在全新场景中也能预测物理交互的结果。当存在期望的推送动作时，人类能够确定在新物体上的施力点位置，从而实现物体运动的可预测性。我们通过将学习过程拆解为两个阶段实现了同类行为。首先，我们学习一组局部接触模型（local contact models），以表征机器人推头、物体与环境间的几何关系；随后，我们学习一组参数化局部运动模型（parametric local motion models），以预测这些接触在推送过程中的变化情况。上述接触模型与运动模型共同构成了我们的内部模型。通过调整物理参数分布的形态，我们可以修改内部模型的响应结果。当对全新场景无任何先验信息时，均匀分布会生成较为粗略的估计结果，我们将其称为无偏预测器（unbiased predictor）。针对特定的环境/物体组合（例如低摩擦/高质量场景），可以训练得到更为精准的预测器，即有偏预测器（biased predictor）。我们的方法有效性在仿真环境中得到了验证：搭载缓冲器的先锋3-DX（Pioneer 3-DX）机器人需要对全新场景中的物体推送结果进行预测；同时，我们在实体机器人上开展了概念验证实验以佐证上述结果。我们在两种物体（立方体与圆柱体）上进行训练，在各类条件下累计完成了24000次推送操作；随后在涵盖不同形状、尺寸与物理参数的6种物体上开展测试，累计生成14400次推送结果预测。实验结果表明，无论是有偏还是无偏预测器，均能够可靠生成与精细调优后的物理模拟器（physics simulator）输出一致的预测结果。