Ronald Kates

Development of an Integrated Test Bed and Virtual Laboratory for Safety Performance Prediction in Active Safety Systems

This paper describes recent progress toward achieving representative and reliable active safety performance assessment of advanced driver assistance systems (ADAS). Because ADAS act within a complex, dynamic traffic environment, reliable evaluation of their safety benefits poses methodological challenges. For a proposed ADAS, its expected contribution to reduction of mortality and injuries as well as false positives should be predicted. To meet these challenges, our approach incorporates identification of target scenarios; calibration and validation of stochastic behavior and accident injury models; stochastic (Monte-Carlo) simulation of target scenarios in varied traffic contexts with/without ADAS; and integration of supporting and corroborating field and laboratory analyses. These include a new controlled, high-throughput approach to sensor testing and algorithm validation in camera-based ADAS using a virtual graphical test bed, which supports systematic identification of critical external conditions that could modify performance or lead to a failure mode. The methodologies introduced here are designed to ensure validity of all key links in the assessment chain, not limited to those aspects that can be assessed in a single test.

Safety Performance Assessment of Assisted and Automated Driving by Virtual Experiments: Stochastic Microscopic Traffic Simulation as Knowledge Synthesis

Advanced driver assistance and automated driving can influence traffic safety in a variety of ways. Development and implementation of safety-relevant functions require prospective, quantitative assessment of their traffic safety impacts. Both benefits and risks can be quantified using simulation-based virtual experimental techniques. To this end, traffic phenomena are modeled taking into account key safety-relevant processes and stochastic simulation is performed on large, representative virtual samples. The virtual representations of traffic phenomena are based on detailed, stochastic models of drivers, vehicles, traffic flow, and the road environment, together with their interactions. The models incorporate knowledge from FOT, NDS, laboratory and driving simulator experiments, and other sources. Large-scale, comprehensive simulations could help in identifying and evaluating the relevant situations in which automated driving impacts traffic safety. The goal is a standardized harmonized methodology, agreed upon by all stakeholders, for holistic assessment of the impact of new driver assistance or automatic driving functions on traffic safety.

Predicting the Injury Severity of Pedestrians in Frontal Vehicle Crashes based on Empirical, In-depth Accident Data

For proposed pedestrian protection systems, evaluation of safety benefits is required as an integral part of the design and optimization phases. Stochastic (“Monte-Carlo”) simulation techniques are currently being utilized to predict safety benefits in terms of physics; however, converting physics to human benefits requires injury and fatality risk models. To this end, multivariate predictive models for pedestrian fatalities and for injury severity on the ISS scale are estimated using the US Pedestrian Crash Data Study (PCDS). In addition to collision speed, which is the most important single explanatory variable, age, pedestrian physiological characteristics and vehicle parameters are significant multivariate predictors. The in-sample as well as out-of-sample predictive quality is remarkably high. The models are intended to provide an interface to large-scale stochastic simulation and virtual testing of proposed vehicle-based active safety systems for pedestrian protection.

Safety Performance Assessment of Assisted and Automated Driving in Traffic: Simulation as Knowledge Synthesis

Advanced driver assistance and automated driving can influence traffic safety in a variety of ways. The development and implementation of safety-relevant functions require prospective, quantitative assessment of their traffic safety impacts. Both benefits and risks can be quantified using simulation-based virtual experimental techniques. To this end, traffic phenomena are modeled taking into account key safety-relevant processes; “stochastic” simulation is performed on large, representative virtual samples. The virtual representations of traffic phenomena are based on detailed, stochastic models of drivers, vehicles, traffic flow, and the road environment, together with their interactions. The models incorporate knowledge from field operational test (FOT), naturalistic driving studies (NDS), laboratory and driving simulator experiments, and other sources. Simulation serves to synthesize this knowledge. Large-scale, comprehensive simulations could help in identifying and evaluating the relevant situations in which automated driving impacts traffic safety. One key objective is a standardized harmonized methodology, agreed upon by all stakeholders, for comprehensive assessment of the impact of new driver assistance or automated driving functions on traffic safety.

Multi-functional open-source simulation platform for development and functional validation of ADAS and automated driving

In modern vehicles, Advanced Driver Assistance Systems (ADAS) and automated driving functions are increasingly playing the role of a co-pilot, supporting the driver in complex or dangerous situations by applying preventive strategies.4 These strategies include warnings, enhanced braking assistance, and automatic interventions to increase road safety. As discussed in [2], these strategies can help to avoid collisions, or – in case of inevitable accidents – mitigate injury severity.