FRESHR-GSI: A Generalized Safety Model and Evaluation Framework for Mobile Robots in Multi-Human Environments

2025-01-07

AI Summary

Existing safety assessment methods for mobile robots in dynamic multi-pedestrian scenarios are inadequate. Method: This paper proposes a robot-centric, targeted human safety assessment framework, introducing the first configurable, viewpoint-adaptive safety modeling paradigm. We define the Generalized Safety Index (GSI), which fuses dynamic features—including relative distance, velocity, and orientation—to enable fine-grained, robust, and real-time quantification of multi-pedestrian risk. The method integrates RGB-D perception, deep-learning-based human detection, and multi-object motion state estimation, supporting dual-perspective evaluation from both the robot’s egocentric view and external observation. Results: Experiments in real-world environments demonstrate that GSI significantly outperforms existing metrics in sensitivity, discriminative power, and response consistency, achieving a 23.6% improvement in assessment accuracy. This work establishes a novel paradigm for human-robot coexistence safety in autonomous systems.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Natural Language Processing: Safety and Robustness
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness

Application Category

• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Human safety is critical in applications involving close human-robot interactions (HRI) and is a key aspect of physical compatibility between humans and robots. While measures of human safety in HRI exist, these mainly target industrial settings involving robotic manipulators. Less attention has been paid to settings where mobile robots and humans share the space. This paper introduces a new robot-centered directional framework of human safety. It is particularly useful for evaluating mobile robots as they operate in environments populated by multiple humans. The framework integrates several key metrics, such as each human's relative distance, speed, and orientation. The core novelty lies in the framework's flexibility to accommodate different application requirements while allowing for both the robot-centered and external observer points of view. We instantiate the framework by using RGB-D based vision integrated with a deep learning-based human detection pipeline to yield a generalized safety index (GSI) that instantaneously assesses human safety. We evaluate GSI's capability of producing appropriate, robust, and fine-grained safety measures in real-world experimental scenarios and compare its performance with extant safety models.

Problem

• Mobile Robotics
• Human Safety
• Assessment Methods

Innovation

• FRESHR-GSI
• Universal Safety Index
• Visual Technology and Deep Learning