Follow-Bench: A Unified Motion Planning Benchmark for Socially-Aware Robot Person Following

2025-09-12

AI Summary

This work addresses the fundamental challenge in socially aware robot following (RPF)—the trade-off between safety and comfort—by introducing the first unified, open-source motion planning benchmark for RPF. The benchmark comprises diverse simulated environments, multimodal target trajectories, and dynamic crowd interactions, enabling systematic evaluation of safety metrics (e.g., collision rate, minimum separation distance) and comfort metrics (e.g., following stability, social distance compliance). It enables the first standardized, end-to-end evaluation of RPF methods. We open-source reproducible implementations of six state-of-the-art planners and validate them both in simulation and on a differential-drive robot platform. Experimental results reveal pervasive bottlenecks in existing approaches’ ability to jointly optimize safety and comfort, identifying key deployment barriers—including sensitivity to crowd density and trajectory unpredictability—and delineating concrete directions for improvement.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Robot person following (RPF) -- mobile robots that follow and assist a specific person -- has emerging applications in personal assistance, security patrols, eldercare, and logistics. To be effective, such robots must follow the target while ensuring safety and comfort for both the target and surrounding people. In this work, we present the first end-to-end study of RPF, which (i) surveys representative scenarios, motion-planning methods, and evaluation metrics with a focus on safety and comfort; (ii) introduces Follow-Bench, a unified benchmark simulating diverse scenarios, including various target trajectory patterns, dynamic-crowd flows, and environmental layouts; and (iii) re-implements six popular RPF planners, ensuring that both safety and comfort are systematically considered. Moreover, we evaluate the two highest-performing planners from our benchmark on a differential-drive robot to provide insights into real-world deployment. Extensive simulation and real-world experiments provide quantitative insights into the safety-comfort trade-offs of existing planners, while revealing open challenges and future research directions.

Problem

• Evaluating robot person following safety and comfort trade-offs
• Benchmarking motion planners in diverse social scenarios
• Assessing real-world deployment challenges for following robots

Innovation

• Unified benchmark simulating diverse scenarios
• Re-implemented six RPF planners systematically
• Evaluated safety-comfort trade-offs extensively