Follow-Me in Micro-Mobility with End-to-End Imitation Learning

TL;DR

This paper presents an imitation learning approach for autonomous micro-mobility, specifically a wheelchair that follows a human operator, achieving improved comfort and real-world deployment capabilities.

Contribution

It introduces an end-to-end imitation learning framework for follow-me micro-mobility, demonstrating superior comfort and real-world applicability over traditional controllers.

Findings

Imitation learning yields smoother, more comfortable control.

The approach outperforms manually-tuned controllers in user comfort.

The system is validated in real-world deployment.

Abstract

Autonomous micro-mobility platforms face challenges from the perspective of the typical deployment environment: large indoor spaces or urban areas that are potentially crowded and highly dynamic. While social navigation algorithms have progressed significantly, optimizing user comfort and overall user experience over other typical metrics in robotics (e.g., time or distance traveled) is understudied. Specifically, these metrics are critical in commercial applications. In this paper, we show how imitation learning delivers smoother and overall better controllers, versus previously used manually-tuned controllers. We demonstrate how DAAV's autonomous wheelchair achieves state-of-the-art comfort in follow-me mode, in which it follows a human operator assisting persons with reduced mobility (PRM). This paper analyzes different neural network architectures for end-to-end control and demonstrates their usability in real-world production-level deployments.