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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Salimpour, Sahar, Catalano, Iacopo, Westerlund, Tomi, Falahi, Mohsen, Queralta, Jorge Peña
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908635877081088
author Salimpour, Sahar
Catalano, Iacopo
Westerlund, Tomi
Falahi, Mohsen
Queralta, Jorge Peña
author_facet Salimpour, Sahar
Catalano, Iacopo
Westerlund, Tomi
Falahi, Mohsen
Queralta, Jorge Peña
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_05158
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Follow-Me in Micro-Mobility with End-to-End Imitation Learning
Salimpour, Sahar
Catalano, Iacopo
Westerlund, Tomi
Falahi, Mohsen
Queralta, Jorge Peña
Robotics
Machine Learning
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.
title Follow-Me in Micro-Mobility with End-to-End Imitation Learning
topic Robotics
Machine Learning
url https://arxiv.org/abs/2511.05158