Dynamic Risk Assessment for Human-Robot Collaboration Using a Heuristics-based Approach

2025-03-11

AI Summary

To address the challenge of dynamically complex human–robot interactions (HRI) in human–robot collaboration (HRC), where conventional risk assessment methods lack real-time adaptability to multi-factor scenarios, this paper proposes a human-centered dynamic risk assessment approach. The method integrates multi-source sensor data to continuously monitor critical parameters—including inter-agent distance, robot Cartesian velocity, and human head orientation—introducing head orientation as an objective behavioral proxy for the first time, thereby eliminating reliance on expert knowledge. A nonlinear heuristic function is designed to compute hazard indicators, which are then aggregated into a quantitative risk score. Experimental evaluation on a real-world industrial HRC dataset demonstrates significant improvements in both real-time responsiveness and contextual adaptability. The framework supports automated safety decision-making compliant with ISO 10218 and ISO/TS 15066, establishing a scalable, verifiable paradigm for collaborative robot (cobot) safety assessment.

Technology Category

• Intelligent Robots: Human-Robot Interaction
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Natural Language Processing: Safety and Robustness

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Human-robot collaboration (HRC) introduces significant safety challenges, particularly in protecting human operators working alongside collaborative robots (cobots). While current ISO standards emphasize risk assessment and hazard identification, these procedures are often insufficient for addressing the complexity of HRC environments, which involve numerous design factors and dynamic interactions. This publication presents a method for objective hazard analysis to support Dynamic Risk Assessment, extending beyond reliance on expert knowledge. The approach monitors scene parameters, such as the distance between human body parts and the cobot, as well as the cobot`s Cartesian velocity. Additionally, an anthropocentric parameter focusing on the orientation of the human head within the collaborative workspace is introduced. These parameters are transformed into hazard indicators using non-linear heuristic functions. The hazard indicators are then aggregated to estimate the total hazard level of a given scenario. The proposed method is evaluated using an industrial dataset that depicts various interactions between a human operator and a cobot.

Problem

• Addresses safety challenges in human-robot collaboration environments.
• Extends risk assessment beyond ISO standards using dynamic parameters.
• Proposes a method for hazard analysis using non-linear heuristic functions.

Innovation

• Heuristics-based dynamic risk assessment method
• Monitors human-cobot distance and velocity
• Introduces anthropocentric head orientation parameter