Automated Brake Onset Detection in Naturalistic Driving Data

2025-07-23

AI Summary

To address the challenge of accurately detecting brake initiation instants in large-scale naturalistic driving data—where brake pedal signals are often unavailable—we propose an automated detection algorithm based on a piecewise linear acceleration model. The method operates solely on longitudinal acceleration time-series data, estimating brake onset by modeling deceleration patterns, thus eliminating reliance on vehicle control signals and ensuring broad applicability and configurability. Evaluated on real-world collision-avoidance scenarios involving both human drivers and autonomous driving systems (ADS), the algorithm achieves an R² > 0.92, a median temporal error < 0.15 s, and classification performance approaching expert manual annotation. This work presents the first high-accuracy, subject-agnostic (human/ADS), and scenario-generalizable automatic brake-onset detection method that requires no brake-pedal signal—significantly enhancing the objectivity and scalability of collision-avoidance response timing assessment.

Technology Category

• Humans and AI: Brain-Sensing and Analysis
• Search and Optimization: Algorithm Configuration
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

Response timing measures play a crucial role in the assessment of automated driving systems (ADS) in collision avoidance scenarios, including but not limited to establishing human benchmarks and comparing ADS to human driver response performance. For example, measuring the response time (of a human driver or ADS) to a conflict requires the determination of a stimulus onset and a response onset. In existing studies, response onset relies on manual annotation or vehicle control signals such as accelerator and brake pedal movements. These methods are not applicable when analyzing large scale data where vehicle control signals are not available. This holds in particular for the rapidly expanding sets of ADS log data where the behavior of surrounding road users is observed via onboard sensors. To advance evaluation techniques for ADS and enable measuring response timing when vehicle control signals are not available, we developed a simple and efficient algorithm, based on a piecewise linear acceleration model, to automatically estimate brake onset that can be applied to any type of driving data that includes vehicle longitudinal time series data. We also proposed a manual annotation method to identify brake onset and used it as ground truth for validation. R2 was used as a confidence metric to measure the accuracy of the algorithm, and its classification performance was analyzed using naturalistic collision avoidance data of both ADS and humans, where our method was validated against human manual annotation. Although our algorithm is subject to certain limitations, it is efficient, generalizable, applicable to any road user and scenario types, and is highly configurable.

Problem

• Detecting brake onset automatically in driving data without control signals
• Providing a method to measure response timing in automated driving systems
• Validating algorithm accuracy against manual brake onset annotations

Innovation

• Piecewise linear acceleration model algorithm
• Manual annotation for ground truth validation
• R2 confidence metric for accuracy measurement