Pedestrians and Robots: A Novel Dataset for Learning Distinct Social Navigation Forces

2025-03-05

arXiv.org

AI Summary

Existing pedestrian–robot interaction datasets lack systematic coverage of socially nuanced responses—such as avoidance, neutrality, and attraction—hindering accurate modeling and prediction. To address this, we introduce the first outdoor pedestrian trajectory dataset explicitly designed across three robot conditions: no robot, static robot, and mobile robot; it is also the first to explicitly decouple the effect of robot presence on pedestrian behavior. We propose the Neural Social Robot Force Model (NSRFM), which embeds robot-induced forces directly into a neural network architecture—overcoming key limitations of classical social force models in human–robot interaction. Evaluated on diverse real-world scenarios, NSRFM achieves significant improvements in trajectory prediction accuracy. Furthermore, we develop a simulation-driven evaluation framework that supports learning, benchmarking, and human–robot co-planning for social navigation algorithms, faithfully reproducing authentic pedestrian social responses.

Technology Category

• Intelligent Robots: Human-Robot Interaction
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• User Modeling, Personalization and Recommendation: Social recommender systems and personalization for the social Web
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search

Abstract

The increasing use of robots in human-centric public spaces such as shopping malls, sidewalks, and hospitals, requires understanding of how pedestrians respond to their presence. However, existing research lacks comprehensive datasets that capture the full range of pedestrian behaviors, e.g., including avoidance, neutrality, and attraction in the presence of robots. Such datasets can be used to effectively learn models capable of accurately predicting diverse responses of pedestrians to robot presence, which are crucial for advancing robot navigation strategies and optimizing pedestrian-aware motion planning. In this paper, we address these challenges by collecting a novel dataset of pedestrian motion in two outdoor locations under three distinct conditions, i.e., no robot presence, a stationary robot, and a moving robot. Thus, unlike existing datasets, ours explicitly encapsulates variations in pedestrian behavior across the different robot conditions. Using our dataset, we propose a novel Neural Social Robot Force Model (NSRFM), an extension of the traditional Social Force Model that integrates neural networks and robot-induced forces to better predict pedestrian behavior in the presence of robots. We validate the NSRFM by comparing its generated trajectories on different real-world datasets. Furthermore, we implemented it in simulation to enable the learning and benchmarking of robot navigation strategies based on their impact on pedestrian movement. Our results demonstrate the model's effectiveness in replicating real-world pedestrian reactions and its its utility in developing, evaluating, and benchmarking social robot navigation algorithms.

Problem

• Captures pedestrian reactions to robots in social navigation
• Models avoidance neutrality attraction behaviors in human-robot interactions
• Improves pedestrian motion prediction near robots using neural networks

Innovation

• Dataset captures pedestrian reactions to robots
• Neural networks enhance Social Force Model dynamics
• Model improves pedestrian motion prediction near robots