From Robot Learning To Robot Understanding: Leveraging Causal Graphical Models For Robotics

Kaylene Caswell Stocking, Alison Gopnik, Claire Tomlin

Keywords: causal reasoning, cognitive science, causal graphical models

TL;DR: We argue that algorithms for generating hypotheses in the form of causal graphical models is an exciting and promising avenue for robotics research.

Abstract: Causal graphical models have been proposed as a way to efficiently and explicitly reason about novel situations and the likely outcomes of decisions. A key challenge facing widespread implementation of these models in robots is using prior knowledge to hypothesize good candidate causal structures when the relevant environmental features are not known in advance. The tight link between causal reasoning and the ability to intervene in the world suggests that robotics has much to contribute to this challenge and would reap significant benefits from progress.