Saved in:
Bibliographic Details
Main Authors: Gómez-Izquierdo, Gerard, Laplaza, Javier, Sanfeliu, Alberto, Garrell, Anaís
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.00576
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917942654926848
author Gómez-Izquierdo, Gerard
Laplaza, Javier
Sanfeliu, Alberto
Garrell, Anaís
author_facet Gómez-Izquierdo, Gerard
Laplaza, Javier
Sanfeliu, Alberto
Garrell, Anaís
contents Accurate human motion prediction (HMP) is critical for seamless human-robot collaboration, particularly in handover tasks that require real-time adaptability. Despite the high accuracy of state-of-the-art models, their computational complexity limits practical deployment in real-world robotic applications. In this work, we enhance human motion forecasting for handover tasks by leveraging siMLPe [1], a lightweight yet powerful architecture, and introducing key improvements. Our approach, named IntentMotion incorporates intention-aware conditioning, task-specific loss functions, and a novel intention classifier, significantly improving motion prediction accuracy while maintaining efficiency. Experimental results demonstrate that our method reduces body loss error by over 50%, achieves 200x faster inference, and requires only 3% of the parameters compared to existing state-of-the-art HMP models. These advancements establish our framework as a highly efficient and scalable solution for real-time human-robot interaction.
format Preprint
id arxiv_https___arxiv_org_abs_2503_00576
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhancing Context-Aware Human Motion Prediction for Efficient Robot Handovers
Gómez-Izquierdo, Gerard
Laplaza, Javier
Sanfeliu, Alberto
Garrell, Anaís
Robotics
Accurate human motion prediction (HMP) is critical for seamless human-robot collaboration, particularly in handover tasks that require real-time adaptability. Despite the high accuracy of state-of-the-art models, their computational complexity limits practical deployment in real-world robotic applications. In this work, we enhance human motion forecasting for handover tasks by leveraging siMLPe [1], a lightweight yet powerful architecture, and introducing key improvements. Our approach, named IntentMotion incorporates intention-aware conditioning, task-specific loss functions, and a novel intention classifier, significantly improving motion prediction accuracy while maintaining efficiency. Experimental results demonstrate that our method reduces body loss error by over 50%, achieves 200x faster inference, and requires only 3% of the parameters compared to existing state-of-the-art HMP models. These advancements establish our framework as a highly efficient and scalable solution for real-time human-robot interaction.
title Enhancing Context-Aware Human Motion Prediction for Efficient Robot Handovers
topic Robotics
url https://arxiv.org/abs/2503.00576