Can I read Interpretability in Contact-Rich Manipulation via Kinodynamic Images on EtoBox?

Interpretability in Contact-Rich Manipulation via Kinodynamic Images by Mitsioni, Ioanna; Mänttäri, Joonatan; Karayiannidis, Yiannis; Folkesson, John; Kragic, Danica is a scholarly article available to read on EtoBox.

What is Interpretability in Contact-Rich Manipulation via Kinodynamic Images about?

Deep Neural Networks (NNs) have been widely utilized in contact-rich manipulation tasks to model the complicated contact dynamics. However, NN-based models are often difficult to decipher which can lead to seemingly inexplicable behaviors and unidentifiable failure cases. In this work, we address the interpretability of NN-based models by introducing the kinodynamic images. We propose a methodology that creates images from the kinematic and dynamic data of a contact-rich manipulation task. Our formulation visually reflects the task's state by encoding its kinodynamic variations and temporal evolution. By using images as the state representation, we enable the application of interpretability modules that were previously limited to vision-based tasks. We use this representation to train Convolution-based Networks and we extract interpretations of the model's decisions with Grad-CAM, a technique that produces visual explanations. Our method is versatile and can be applied to any classification problem using synchronous features in manipulation to visually interpret which parts of the input drive the model's decisions and distinguish its failure modes. We evaluate this approach on two

Author

Mitsioni, Ioanna; Mänttäri, Joonatan; Karayiannidis, Yiannis; Folkesson, John; Kragic, Danica

Published

2021

Language

EN