Navigating the Crowd: Non-linear MPC with Social Forces Dynamics for Human-Aware Robot Navigation

Jul 16, 2026

Upload by Asher

Safe, socially compliant navigation in human-populated environments requires more than collision avoidance: robots must anticipate human motion and preserve personal space to maintain comfort. Model Predictive Control (MPC) can plan over a finite horizon, but depends on accurate human prediction and real-time computation. The work presents SFM-NMPC, embedding the Social Force Model into a non-linear MPC optimization loop, jointly predicting human and robot trajectories with tailored social cost functions. The method runs at 20 Hz and improves social compliance in crowded simulations while ensuring smooth navigation.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages9

Reading Time23 min

Abstract

Introduction

Navigating the Crowd: Non-linear MPC with Social Forces Dynamics for Human-Aware Robot Navigation Stefano Trepella 1 , Andrea Ostuni 1 , Mauro Martini 1 , Pablo Pueyo2 , No Prez-Higueras2 , Marcello Chiaberge 1 , Fernando Caballero2 , and Luis Merino2 arXiv :2607 . 10374v1 [ cs .RO] 11 Jul 2026 Abstract—Safe and socially compliant navigation remains a fundamental challenge for autonomous robots operating inhuman-populated environments. Beyond collision avoidance, robots must anticipate human motion and respect personal space to ensure human comfort. Model Predictive Control (MPC) offers a robust alternative to classical and data-driven methods, although its effectiveness strongly depends on accurate human motion prediction and efficient computation. This paper introduces SFM-NMPC, a Social Force Modelbased Non-linear Model Predictive Control framework that embeds human motion prediction directly within the optimization loop. By incorporating the Social Force Model into the dynamic model of surrounding agents, the controller jointly predicts the trajectories of humans and robots over the prediction horizon, thereby enabling socially-aware planning. A tailored set of social cost functions guides the optimization toward human-compliant behaviors. Despite the increased model complexity, the proposed formulation runs in real time at 20 Hz. Extensive simulated testing in crowded environments demonstrates that SFM-NMPC outperforms state-of-the-art baselinesin social compliance metrics while maintaining efficient and smooth navigation. Visual trajectory analysis and an ablation study further highlight the contribution of the embedded SFM dynamics and social cost terms, confirming the effectiveness of the proposed approach for real-world social navigation. I. INTRODUCTION Autonomous robots operating in real-world environments must navigate both efficiently and safely, especially when interacting with humans. As the number of robots integrated into everyday tasks continues to increase, ranging from domestic robots [1] to healthcare assistants in hospitals [2], This work was partially supported by the SWIch action (P.R. F.E.S.R.2021/27-D.G.R. n.19-6962) within the EMPATHY project, and by PoliTO Interdepartmental Centre for Service Robotics (PIC4SeR) . It is also partially supported by the project AI-FUSE (SAIA202500X163851SV0) and COBUILD (PID2024-161069OB-C31), funded by the Spanish Research Agency and the Ministry of Science and the European Union (MCIN /AEI/10.13039/501100011033) and by ERDF ”A way of making Europe” 1Department of Electronics and Telecommunications, Politecnico di Torino, 10129, Torino, Italy. stefano .trepella@polito .it, andrea .ostuni@polito .it, mauro .martini@polito .it, marcello .chiaberge@polito .it 2 School of Engineering, Pablo de Olavide University, Crta. Utrera km 1, Seville, Spain [ppueyor@upo.es](ppueyor@upo.es) , [noeperez@upo.es](noeperez@upo.es) , [fcaballero@upo.es](fcaballero@upo.es) , [lmercab@upo.es](lmercab@upo.es) © 2026 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. This is the accepted version of a paper accepted for publication at the 2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), September 27–October 1, 2026, Pittsburgh, PA, USA. The final published version will be available via IEEE Xplore. and autonomous wheelchairs for airport mobility [3], the need for effective human-robot interaction models becomes critical [4] . Fig. 1: SFM-NMPC embeds the Social Force Model in the prediction model of a Non-linear MPC controller as well as in the custom social cost terms to enhance human comfort and safety. Recent

FAQs

What problem does the paper address in human-aware robot navigation?

It addresses safe, socially compliant navigation beyond collision avoidance, requiring robots to anticipate human motion and respect personal space for comfort.

How does SFM-NMPC differ from conventional MPC approaches?

SFM-NMPC embeds the Social Force Model into the non-linear MPC dynamic model, so human and robot trajectories are predicted jointly within the optimization loop.

What is the computational performance of the proposed controller?

The proposed formulation runs in real time at 20 Hz despite increased model complexity.

Jul 16, 2026

Upload by Asher