Psychology · MapleScholar Plus

Walking with Humans: Non-linear MPC with Social Forces for Autonomous Robot Navigation

Autonomous delivery robots and hospital rovers frequently froze in place or cut off pedestrians in crowded corridors; integrating Helbing's social force dynamics into non-linear model predictive control enables natural, socially compliant robot navigation.

Author
Stefano Trepella et al.
Published
2026
Journal
arXiv (Cornell University)
Last updated
September 2026
Walking with Humans: Non-linear MPC with Social Forces for Autonomous Robot Navigation

Autonomous service robots are increasingly deployed in airports, shopping malls, and hospitals to deliver medications, sanitize hallways, and transport luggage.

In dense human crowds, conventional robotic obstacle avoidance algorithms fail: robots perceive moving pedestrians as static obstacles, freezing in place (the 'freezing robot problem') or making erratic, uncomfortable maneuvers.

This robotics paper integrates Helbing's psychological social force model directly into a non-linear Model Predictive Control (NMPC) optimization framework. By treating pedestrians not as rigid barriers but as dynamic agents that respond to social repulsive and attractive forces, the robot anticipates crowd flow and navigates with human-like smoothness.

Socially compliant trajectory planning allows service robots to blend seamlessly into urban pedestrian spaces, fostering public trust and enabling safe human-robot coexistence in shared environments.

Reference

Trepella, S., Ostuni, A., Martini, M., Pueyo, P., Pérez-Higueras, N., Chiaberge, M., Caballero, F., & Merino, L. (2026). Navigating the Crowd: Non-linear MPC with Social Forces Dynamics for Human-Aware Robot Navigation (Version 1). arXiv.

Title

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

Abstract

Safe and socially compliant navigation remains a fundamental challenge for autonomous robots operating in human-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 Model-based 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 baselines in 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.

Cited 0 times · View on doi.org

Continue

Continue Exploring

Ask this paper your own questions, or keep browsing the verified research catalogue.