Composite Safety Potential Field for Highway Driving Risk Assessment

2025-04-29

AI Summary

Existing driving risk assessment models suffer from poor calibration, overreliance on sparse crash data, and limited generalizability across longitudinal and lateral dimensions, hindering accurate potential collision identification and human–machine collaborative decision-making. To address these limitations, we propose the Composite Safety Potential Field (C-SPF), the first framework unifying longitudinal and lateral risk modeling. C-SPF integrates a subjective potential field—encoding driver-perceived spatial proximity—with an objective potential field—quantifying instantaneous collision probability—enabling real-time, interpretable risk assessment in high-speed scenarios. Crucially, it requires only abundant two-dimensional inter-vehicle distance data for calibration, eliminating dependence on crash statistics. Moreover, C-SPF accurately characterizes complex safety-critical responses, including lane-change abandonment and lateral evasive maneuvers. Evaluated on naturalistic driving datasets, C-SPF significantly improves detection accuracy of risk events and enhances interpretability of lateral behaviors (e.g., lane-change inhibition), outperforming state-of-the-art potential-field-based models.

Technology Category

• Natural Language Processing: Safety and Robustness
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

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

Abstract

In the era of rapid advancements in vehicle safety technologies, driving risk assessment has become a focal point of attention. Technologies such as collision warning systems, advanced driver assistance systems (ADAS), and autonomous driving require driving risks to be evaluated proactively and in real time. To be effective, driving risk assessment metrics must not only accurately identify potential collisions but also exhibit human-like reasoning to enable safe and seamless interactions between vehicles. Existing safety potential field models assess driving risks by considering both objective and subjective safety factors. However, their practical applicability in real-world risk assessment tasks is limited. These models are often challenging to calibrate due to the arbitrary nature of their structures, and calibration can be inefficient because of the scarcity of accident statistics. Additionally, they struggle to generalize across both longitudinal and lateral risks. To address these challenges, we propose a composite safety potential field framework, namely C-SPF, involving a subjective field to capture drivers' risk perception about spatial proximity and an objective field to quantify the imminent collision probability, to comprehensively evaluate driving risks. The C-SPF is calibrated using abundant two-dimensional spacing data from trajectory datasets, enabling it to effectively capture drivers' proximity risk perception and provide a more realistic explanation of driving behaviors. Analysis of a naturalistic driving dataset demonstrates that the C-SPF can capture both longitudinal and lateral risks that trigger drivers' safety maneuvers. Further case studies highlight the C-SPF's ability to explain lateral driver behaviors, such as abandoning lane changes or adjusting lateral position relative to adjacent vehicles, which are capabilities that existing models fail to achieve.

Problem

• Develops a composite safety potential field for highway risk assessment
• Addresses limitations in existing risk models' calibration and generalization
• Captures both longitudinal and lateral driving risks effectively

Innovation

• Composite safety potential field for risk assessment
• Combines subjective and objective safety fields
• Calibrated using 2D spacing data from trajectories