Learning where to trust unreliable models in an unstructured world for deformable object manipulation
Learning where to trust unreliable models in an unstructured world for deformable object manipulation
复制标题
DOI：
10.1126/scirobotics.abd8170
复制
发表时间：
2021-05-26
期刊：
影响因子：
25
通讯作者：
Berenson, D.
中科院分区：
文献类型：
--
作者：
Mitrano, P.;McConachie, D.;Berenson, D.
我们实验室之外的世界很少符合我们模型的假设。对于用于像可变形物体这样的复杂高自由度系统的控制和运动规划的动力学模型来说，尤其如此。我们必须开发更好的模型，但我们也必须考虑到，无论我们的模拟器有多强大，数据集有多大，我们的模型有时会出错。而且，估计模型的错误程度可能很困难，因为基于训练数据预测不确定性分布的方法无法考虑到未见过的情况。要在非结构化环境中部署机器人，我们必须解决两个关键问题：我们何时应该信任一个模型，以及如果机器人处于模型不可靠的状态我们该怎么做。我们在杂乱环境中规划操作绳索状物体的背景下解决这些问题。在此，我们报告一种方法，该方法在无约束的环境中学习一个模型，然后学习一个分类器，以便在给定有限的绳索约束相互作用数据集的情况下，预测该模型在何处有效。我们还提出一种从我们的模型预测不可靠的状态中恢复的方法。我们的方法在统计上显著优于学习一个动力学函数并在任何地方都信任它。我们进一步在几个家庭和汽车任务的实际模型上展示了我们方法的实用性。
The world outside our laboratories seldom conforms to the assumptions of our models. This is especially true for dynamics models used in control and motion planning for complex high-degree of freedom systems like deformable objects. We must develop better models, but we must also consider that, no matter how powerful our simulators or how big our datasets, our models will sometimes be wrong. What is more, estimating how wrong models are can be difficult, because methods that predict uncertainty distributions based on training data do not account for unseen scenarios. To deploy robots in unstructured environments, we must address two key questions: When should we trust a model and what do we do if the robot is in a state where the model is unreliable. We tackle these questions in the context of planning for manipulating rope-like objects in clutter. Here, we report an approach that learns a model in an unconstrained setting and then learns a classifier to predict where that model is valid, given a limited dataset of rope-constraint interactions. We also propose a way to recover from states where our model prediction is unreliable. Our method statistically significantly outperforms learning a dynamics function and trusting it everywhere. We further demonstrate the practicality of our method on real-world mock-ups of several domestic and automotive tasks.