机器人控制鲁棒性中的反事实解释和因果推理
Counterfactual Explanation and Causal Inference in Service of Robustness in Robot Control
摘要：
我们提出了一个架构，用于训练生成模型的反事实条件的形式，'我们可以修改事件A导致B而不是C？”，在机器人控制中的应用。使用“对抗训练”范例，训练基于图像的深度神经网络模型，以对原始图像进行小而逼真的修改，以产生用户定义的效果。这些修改可以在基于图像的鲁棒控制的设计过程中使用，以确定控制器通过修改输入空间而不是通过自适应返回到工作状态的能力。与传统的控制设计方法相比，鲁棒性在拒绝噪声的能力方面被量化，我们探索了可能导致违反某些要求的反事实空间，从而提出了一种在某些机器人应用中可能更具表现力的替代模型。因此，我们提出了反事实的产生作为一种方法来解释的黑盒子模型和自主机器人控制的潜在运动路径的设想。首先，我们使用众所周知的MNIST和CelebFaces属性数据集在一组分类任务中演示了这种方法。然后，解决多维回归，我们证明了我们的方法，在一个物理机器人达到任务，并在导航任务与机器人在数字孪生模拟。
英文摘要：
We propose an architecture for training generative models of counterfactual conditionals of the form, 'can we modify event A to cause B instead of C?', motivated by applications in robot control. Using an 'adversarial training' paradigm, an image-based deep neural network model is trained to produce small and realistic modifications to an original image in order to cause user-defined effects. These modifications can be used in the design process of image-based robust control - to determine the ability of the controller to return to a working regime by modifications in the input space, rather than by adaptation. In contrast to conventional control design approaches, where robustness is quantified in terms of the ability to reject noise, we explore the space of counterfactuals that might cause a certain requirement to be violated, thus proposing an alternative model that might be more expressive in certain robotics applications. So, we propose the generation of counterfactuals as an approach to explanation of black-box models and the envisioning of potential movement paths in autonomous robotic control. Firstly, we demonstrate this approach in a set of classification tasks, using the well known MNIST and CelebFaces Attributes datasets. Then, addressing multi-dimensional regression, we demonstrate our approach in a reaching task with a physical robot, and in a navigation task with a robot in a digital twin simulation.
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。
