Demonstration Based Explainable AI for Learning from Demonstration Methods

TL;DR

This paper presents an adaptive explainable AI system for Learning from Demonstration that improves robot teaching efficiency and user understanding by providing tailored trajectory feedback during a navigation task.

Contribution

It introduces an adaptive explanatory feedback mechanism within an inverse reinforcement learning framework for LfD, enhancing interpretability and teaching effectiveness.

Findings

Improved robot performance with explanatory feedback.

Enhanced user understanding of robot behavior.

Increased teaching efficiency in user study.

Abstract

Learning from Demonstration (LfD) is a powerful type of machine learning that can allow novices to teach and program robots to complete various tasks. However, the learning process for these systems may still be difficult for novices to interpret and understand, making effective teaching challenging. Explainable artificial intelligence (XAI) aims to address this challenge by explaining a system to the user. In this work, we investigate XAI within LfD by implementing an adaptive explanatory feedback system on an inverse reinforcement learning (IRL) algorithm. The feedback is implemented by demonstrating selected learnt trajectories to users. The system adapts to user teaching by categorizing and then selectively sampling trajectories shown to a user, to show a representative sample of both successful and unsuccessful trajectories. The system was evaluated through a user study with 26 participants teaching a robot a navigation task. The results of the user study demonstrated that the proposed explanatory feedback system can improve robot performance, teaching efficiency and user understanding of the robot.