Bidirectional Human-AI Learning in Real-Time Disoriented Balancing

TL;DR

This paper introduces a real-time bidirectional learning system where humans and AI collaboratively learn and teach balancing skills using a visual inverted pendulum, simulating disorientation scenarios in piloting and spaceflight.

Contribution

It presents a novel real-time system enabling mutual human-AI learning and teaching in a balancing task, demonstrating the dynamic interaction effects.

Findings

AI assistance improves human balancing performance

Human feedback enhances AI model accuracy

Bidirectional learning accelerates skill acquisition

Abstract

We present a real-time system that enables bidirectional human-AI learning and teaching in a balancing task that is a realistic analogue of disorientation during piloting and spaceflight. A human subject and autonomous AI model of choice guide each other in maintaining balance using a visual inverted pendulum (VIP) display. We show how AI assistance changes human performance and vice versa.