Counterfactual Explanation and Causal Inference in Service of Robustness in Robot Control

TL;DR

This paper introduces a generative model for counterfactuals in robot control, enabling the design of input modifications to test robustness and explain black-box models in autonomous robotics.

Contribution

It presents an adversarial training framework for generating realistic counterfactuals to improve robustness and interpretability in robotic control systems.

Findings

Effective in classification tasks with MNIST and CelebFaces datasets.

Demonstrated in robotic reaching and navigation tasks.

Offers an alternative to traditional robustness measures.

Abstract

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.