Towards Probabilistic Causal Discovery, Inference & Explanations for Autonomous Drones in Mine Surveying Tasks

TL;DR

This paper proposes a probabilistic causal framework for autonomous drones in mine surveying, enabling better decision-making and explanations amidst environmental uncertainties and challenges.

Contribution

It introduces a novel framework combining causally-informed planning, online SCM adaptation, and counterfactual explanations for autonomous drone operations.

Findings

Framework addresses confounders and non-stationarity in mine environments

Plans for experimental validation in simulation and real-world datasets

Aims to improve decision-making and interpretability of drone actions

Abstract

Causal modelling offers great potential to provide autonomous agents the ability to understand the data-generation process that governs their interactions with the world. Such models capture formal knowledge as well as probabilistic representations of noise and uncertainty typically encountered by autonomous robots in real-world environments. Thus, causality can aid autonomous agents in making decisions and explaining outcomes, but deploying causality in such a manner introduces new challenges. Here we identify challenges relating to causality in the context of a drone system operating in a salt mine. Such environments are challenging for autonomous agents because of the presence of confounders, non-stationarity, and a difficulty in building complete causal models ahead of time. To address these issues, we propose a probabilistic causal framework consisting of: causally-informed POMDP planning, online SCM adaptation, and post-hoc counterfactual explanations. Further, we outline planned experimentation to evaluate the framework integrated with a drone system in simulated mine environments and on a real-world mine dataset.