Probabilistic Human Intent Prediction for Mobile Manipulation:   An Evaluation with Human-Inspired Constraints

Cesar Alan Contreras; Manolis Chiou; Alireza Rastegarpanah; Michal Szulik; Rustam Stolkin

doi:10.1007/s10846-026-02362-4

Probabilistic Human Intent Prediction for Mobile Manipulation: An Evaluation with Human-Inspired Constraints

Cesar Alan Contreras
, Manolis Chiou
, Alireza Rastegarpanah
, Michal Szulik
, Rustam Stolkin

Research output: Contribution to journal › Article › peer-review

Abstract

We present GUIDER (Global User Intent Dual-phase Estimation for Robots), a dual-phase probabilistic framework for intent inference in mobile manipulation that operates without predefined goals. A Synergy Map fuses motion evidence with an occupancy grid to rank likely interaction areas during navigation. After arrival, perception merges U-Net and FastSAM saliency with three geometric grasp-feasibility tests; an end-effector kinematics-aware update then evolves object probabilities in real time. In 100 teleoperation trials (20 participants 5 tasks) in Isaac Sim, GUIDER outperformed baselines. During navigation, median stability was 100% across tasks (BOIR, the baseline, had an overall median of 89.85%), with large gains under redirection (BOIR 59.67–63.49% in T2/T5). During manipulation, median stability was 100% in all tasks, while Trajectron (manipulation baseline) dropped to 62.68% for tool grasping (T4). GUIDER yielded earlier confident object predictions in geometry-constrained settings (T5: 20.31 s remaining vs 3.89 s). Ablations confirm the need for the multi-horizon synergy map, the grasp-feasibility checks, and temporal end-effector probability evolution. GUIDER provides a unified probabilistic backbone spanning base and arm, supporting future variable-autonomy controllers.

Original language	English
Article number	36
Number of pages	22
Journal	Journal of Intelligent and Robotic Systems: Theory and Applications
Volume	112
Issue number	2
Early online date	5 Mar 2026
DOIs	https://doi.org/10.1007/s10846-026-02362-4
Publication status	E-pub ahead of print - 5 Mar 2026

Bibliographical note

Copyright © The Author(s) 2026. This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adap-tation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indi-cate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copy-right holder. To view a copy of this licence, visit https://creativecommons.org/licenses/by/4.0/

Data Access Statement

The datasets generated and analysed during the current study are available from the corresponding author upon reasonable request.

Funding

This work was funded by the Nuclear Decommissioning Authority (NDA) and supported by the United Kingdom National Nuclear Laboratory (UKNNL). In addition, it was supported by the UK Research and Innovation (UKRI) project “REBELION” under Grant 10079049.

Funders	Funder number
Nuclear Decommissioning Authority
UK Research and Innovation	10079049

Keywords

Variable Autonomy
Intent Inference
Logical Constraints
Human-Robot Interaction
Mobile Manipulation
Human Intent

Access to Document

10.1007/s10846-026-02362-4Licence: CC BY 4.0

Probabilistic Human Intent Prediction for Mobile Manipulation An Evaluation with Human-Inspired Constraints
Copyright © The Author(s) 2026. This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adap-tation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indi-cate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copy-right holder. To view a copy of this licence, visit https://creativecommons.org/licenses/by/4.0/
Final published version, 5.28 MBLicence: CC BY 4.0

Cite this

@article{d805f4e755d94592967ce5dd3c8f8fd7,

title = "Probabilistic Human Intent Prediction for Mobile Manipulation: An Evaluation with Human-Inspired Constraints",

abstract = "We present GUIDER (Global User Intent Dual-phase Estimation for Robots), a dual-phase probabilistic framework for intent inference in mobile manipulation that operates without predefined goals. A Synergy Map fuses motion evidence with an occupancy grid to rank likely interaction areas during navigation. After arrival, perception merges U-Net and FastSAM saliency with three geometric grasp-feasibility tests; an end-effector kinematics-aware update then evolves object probabilities in real time. In 100 teleoperation trials (20 participants 5 tasks) in Isaac Sim, GUIDER outperformed baselines. During navigation, median stability was 100\% across tasks (BOIR, the baseline, had an overall median of 89.85\%), with large gains under redirection (BOIR 59.67–63.49\% in T2/T5). During manipulation, median stability was 100\% in all tasks, while Trajectron (manipulation baseline) dropped to 62.68\% for tool grasping (T4). GUIDER yielded earlier confident object predictions in geometry-constrained settings (T5: 20.31 s remaining vs 3.89 s). Ablations confirm the need for the multi-horizon synergy map, the grasp-feasibility checks, and temporal end-effector probability evolution. GUIDER provides a unified probabilistic backbone spanning base and arm, supporting future variable-autonomy controllers.",

keywords = "Variable Autonomy, Intent Inference, Logical Constraints, Human-Robot Interaction, Mobile Manipulation, Human Intent",

author = "Contreras, \{Cesar Alan\} and Manolis Chiou and Alireza Rastegarpanah and Michal Szulik and Rustam Stolkin",

note = "Copyright {\textcopyright} The Author(s) 2026. This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adap-tation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indi-cate if changes were made. The images or other third party material in this article are included in the article{\textquoteright}s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article{\textquoteright}s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copy-right holder. To view a copy of this licence, visit https://creativecommons.org/licenses/by/4.0/",

year = "2026",

month = mar,

day = "5",

doi = "10.1007/s10846-026-02362-4",

language = "English",

volume = "112",

number = "2",

}

TY - JOUR

T1 - Probabilistic Human Intent Prediction for Mobile Manipulation

T2 - An Evaluation with Human-Inspired Constraints

AU - Contreras, Cesar Alan

AU - Chiou, Manolis

AU - Rastegarpanah, Alireza

AU - Szulik, Michal

AU - Stolkin, Rustam

N1 - Copyright © The Author(s) 2026. This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adap-tation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indi-cate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copy-right holder. To view a copy of this licence, visit https://creativecommons.org/licenses/by/4.0/

PY - 2026/3/5

Y1 - 2026/3/5

N2 - We present GUIDER (Global User Intent Dual-phase Estimation for Robots), a dual-phase probabilistic framework for intent inference in mobile manipulation that operates without predefined goals. A Synergy Map fuses motion evidence with an occupancy grid to rank likely interaction areas during navigation. After arrival, perception merges U-Net and FastSAM saliency with three geometric grasp-feasibility tests; an end-effector kinematics-aware update then evolves object probabilities in real time. In 100 teleoperation trials (20 participants 5 tasks) in Isaac Sim, GUIDER outperformed baselines. During navigation, median stability was 100% across tasks (BOIR, the baseline, had an overall median of 89.85%), with large gains under redirection (BOIR 59.67–63.49% in T2/T5). During manipulation, median stability was 100% in all tasks, while Trajectron (manipulation baseline) dropped to 62.68% for tool grasping (T4). GUIDER yielded earlier confident object predictions in geometry-constrained settings (T5: 20.31 s remaining vs 3.89 s). Ablations confirm the need for the multi-horizon synergy map, the grasp-feasibility checks, and temporal end-effector probability evolution. GUIDER provides a unified probabilistic backbone spanning base and arm, supporting future variable-autonomy controllers.

AB - We present GUIDER (Global User Intent Dual-phase Estimation for Robots), a dual-phase probabilistic framework for intent inference in mobile manipulation that operates without predefined goals. A Synergy Map fuses motion evidence with an occupancy grid to rank likely interaction areas during navigation. After arrival, perception merges U-Net and FastSAM saliency with three geometric grasp-feasibility tests; an end-effector kinematics-aware update then evolves object probabilities in real time. In 100 teleoperation trials (20 participants 5 tasks) in Isaac Sim, GUIDER outperformed baselines. During navigation, median stability was 100% across tasks (BOIR, the baseline, had an overall median of 89.85%), with large gains under redirection (BOIR 59.67–63.49% in T2/T5). During manipulation, median stability was 100% in all tasks, while Trajectron (manipulation baseline) dropped to 62.68% for tool grasping (T4). GUIDER yielded earlier confident object predictions in geometry-constrained settings (T5: 20.31 s remaining vs 3.89 s). Ablations confirm the need for the multi-horizon synergy map, the grasp-feasibility checks, and temporal end-effector probability evolution. GUIDER provides a unified probabilistic backbone spanning base and arm, supporting future variable-autonomy controllers.

KW - Variable Autonomy

KW - Intent Inference

KW - Logical Constraints

KW - Human-Robot Interaction

KW - Mobile Manipulation

KW - Human Intent

UR - https://link.springer.com/article/10.1007/s10846-026-02362-4

UR - https://www.scopus.com/pages/publications/105035353040

U2 - 10.1007/s10846-026-02362-4

DO - 10.1007/s10846-026-02362-4

M3 - Article

SN - 0921-0296

VL - 112

JO - Journal of Intelligent and Robotic Systems: Theory and Applications

JF - Journal of Intelligent and Robotic Systems: Theory and Applications

IS - 2

M1 - 36

ER -

Probabilistic Human Intent Prediction for Mobile Manipulation: An Evaluation with Human-Inspired Constraints

Abstract

Bibliographical note

Data Access Statement

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Probabilistic Human Intent Prediction for Mobile Manipulation: An Evaluation with Human-Inspired Constraints

Cite this