Toward Global Intent Inference for Human Motion by Inverse Reinforcement Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mehrdad, Sarmad, Sabbah, Maxime, Bonnet, Vincent, Righetti, Ludovic
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917324186976256
author Mehrdad, Sarmad
Sabbah, Maxime
Bonnet, Vincent
Righetti, Ludovic
author_facet Mehrdad, Sarmad
Sabbah, Maxime
Bonnet, Vincent
Righetti, Ludovic
contents This paper investigates whether a single, unified cost function can explain and predict human reaching movements, in contrast with existing approaches that rely on subject- or posture-specific optimization criteria. Using the Minimal Observation Inverse Reinforcement Learning (MO-IRL) algorithm, together with a seven-dimensional set of candidate cost terms, we efficiently estimate time-varying cost weights for a standard planar reaching task. MO-IRL provides orders-of-magnitude faster convergence than bilevel formulations, while using only a fraction of the available data, enabling the practical exploration of time-varying cost structures. Three levels of generality are evaluated: Subject-Dependent Posture-Dependent, Subject-Dependent Posture-Independent, and Subject-Independent Posture-Independent. Across all cases, time-varying weights substantially improve trajectory reconstruction, yielding an average 27% reduction in RMSE compared to the baseline. The inferred costs consistently highlight a dominant role for joint-acceleration regulation, complemented by smaller contributions from torque-change smoothness. Overall, a single subject- and posture-agnostic time-varying cost function is shown to predict human reaching trajectories with high accuracy, supporting the existence of a unified optimality principle governing this class of movements.
format Preprint
id arxiv_https___arxiv_org_abs_2603_07797
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Toward Global Intent Inference for Human Motion by Inverse Reinforcement Learning
Mehrdad, Sarmad
Sabbah, Maxime
Bonnet, Vincent
Righetti, Ludovic
Robotics
Machine Learning
This paper investigates whether a single, unified cost function can explain and predict human reaching movements, in contrast with existing approaches that rely on subject- or posture-specific optimization criteria. Using the Minimal Observation Inverse Reinforcement Learning (MO-IRL) algorithm, together with a seven-dimensional set of candidate cost terms, we efficiently estimate time-varying cost weights for a standard planar reaching task. MO-IRL provides orders-of-magnitude faster convergence than bilevel formulations, while using only a fraction of the available data, enabling the practical exploration of time-varying cost structures. Three levels of generality are evaluated: Subject-Dependent Posture-Dependent, Subject-Dependent Posture-Independent, and Subject-Independent Posture-Independent. Across all cases, time-varying weights substantially improve trajectory reconstruction, yielding an average 27% reduction in RMSE compared to the baseline. The inferred costs consistently highlight a dominant role for joint-acceleration regulation, complemented by smaller contributions from torque-change smoothness. Overall, a single subject- and posture-agnostic time-varying cost function is shown to predict human reaching trajectories with high accuracy, supporting the existence of a unified optimality principle governing this class of movements.
title Toward Global Intent Inference for Human Motion by Inverse Reinforcement Learning
topic Robotics
Machine Learning
url https://arxiv.org/abs/2603.07797