Deep Causal Learning for Robotic Intelligence

TL;DR

This paper reviews the integration of deep causal learning techniques into robotic intelligence, highlighting recent advances, architectures, and the gap between current methods and robotic needs.

Contribution

It provides a comprehensive overview of deep causal learning algorithms and discusses their potential and limitations for robotic applications.

Findings

Deep causal learning algorithms have diverse architectures.

Deep nets enhance causal inference capabilities.

Significant gap remains between deep causal methods and robotic needs.

Abstract

This invited review discusses causal learning in the context of robotic intelligence. The paper introduced the psychological findings on causal learning in human cognition, then it introduced the traditional statistical solutions on causal discovery and causal inference. The paper reviewed recent deep causal learning algorithms with a focus on their architectures and the benefits of using deep nets and discussed the gap between deep causal learning and the needs of robotic intelligence.