Causal Reinforcement Learning for Optimisation of Robot Dynamics in Unknown Environments

TL;DR

This paper presents a novel causal reinforcement learning approach that enables robots to learn causal relationships between object features and dynamics, significantly improving decision-making in unknown environments like urban SAR scenarios.

Contribution

It introduces a new Causal RL architecture for robotics that learns causal links between visual features and object dynamics, enhancing performance in unknown environments.

Findings

Reduced learning times by over 24.5% in complex scenarios

Demonstrated superior performance over non-causal models

Effective causal discovery in robotic interactions

Abstract

Autonomous operations of robots in unknown environments are challenging due to the lack of knowledge of the dynamics of the interactions, such as the objects' movability. This work introduces a novel Causal Reinforcement Learning approach to enhancing robotics operations and applies it to an urban search and rescue (SAR) scenario. Our proposed machine learning architecture enables robots to learn the causal relationships between the visual characteristics of the objects, such as texture and shape, and the objects' dynamics upon interaction, such as their movability, significantly improving their decision-making processes. We conducted causal discovery and RL experiments demonstrating the Causal RL's superior performance, showing a notable reduction in learning times by over 24.5% in complex situations, compared to non-causal models.