E-CoDrive: A Co-Simulation Framework for Testing Energy-Critical Driving Scenarios

Numerical analysis of WoW sensor architecture for energy efficient e-VTOL systems

The rapid development of electric Vertical Take off and Landing (e-VTOL) aircraft as a sustainable urban air mobility solution has highlighted the critical role of avionic systems in overall energy efficiency. Weight on Wheel (WoW) sensors responsible for detecting ground-air transition states directly influence power management decisions onboard e-VTOL. However, the energy consumption implications of varying WoW sensor architectures remain poorly understood, particularly under dynamic ground-air transition conditions. This paper presents a numerical simulation-based analysis of three WoW sensor architectures: single-threshold, redundant dual-channel, and sensor-fusion configurations, evaluating their performance in terms of detection accuracy, response latency, and onboard energy consumption. Simulations were conducted using a finite element numerical model replicating e-VTOL ground-air transition dynamics across 120 flight cycle scenarios. Results indicate that the sensor-fusion architecture achieved the highest detection accuracy at 98.7%, with a mean response latency of 12.3 ms, while reducing energy consumption by 23.7% compared to the redundant dual-channel configuration. The single-threshold architecture, although consuming the least power, demonstrated a detection error rate of 6.2%, rendering it unsuitable for safety-critical operations. These findings suggest that sensor-fusion architecture offers the optimal balance between reliability and energy efficiency for e-VTOL applications.

Validation of a driver model for energy consumption simulations of road vehicles

The energy performance of road vehicles has traditionally been evaluated using driving cycles, in which a prescribed speed profile is tracked either in simulation or by a physical vehicle. Recent research has proposed an alternative framework based on operating conditions, where the driving environment is described in terms of factors such as road topography, legal speed limits, traffic, and weather, rather than by an explicit speed profile. This paper addresses the complementary problem of driver modeling, necessary to translate the operating conditions to a speed profile. A simple driver model designed to be compatible with the operating-condition framework and evaluates its ability to reproduce realistic driving behavior is investigated. Validation of the model is done through a controlled driving-simulator study vehicle log files collected during real-world operation and are used to identify the model parameters and assess the model's predictive performance. The results suggest that this simple model can be efficient in reproducing major effects of driver behavior, while further research is required to fully assess its validity.

A Simulation-Based Assessment of Energy Flow, Efficiency, and Emissions in a Battery Electric Vehicle

This study investigates the performance, energy flow, efficiency, and environmental impact of a C-segment battery electric vehicle (BEV). As BEVs are increasingly considered a sustainable alternative to conventional internal combustion engine vehicles, a detailed understanding of their energy utilization and operational emissions is essential. A MATLAB/Simulink-based vehicle model incorporating an 88.5 kWh battery pack, a 160 kW permanent magnet synchronous motor (PMSM), regenerative braking, and longitudinal vehicle dynamics was developed. The developed model was validated by comparing the simulated vehicle performance characteristics with the publicly available specifications and performance data of the reference TOGG T10F vehicle. The vehicle was evaluated under the WLTP Class 3 driving cycle, while the effects of aggressive and high-speed driving conditions were further investigated using the US06 and Artemis Motorway 150 cycles. The results indicate a net vehicle energy consumption of 136.4 Wh/km and a driving range of 623 km under WLTP conditions. The PMSM achieved average efficiencies of 93.4% in traction mode and 92.7% in regenerative braking mode, while the cumulative battery-to-wheel drivetrain efficiency reached 81.5%. In addition, approximately 19.9% of the consumed energy was recovered through regenerative braking. Vehicle emissions were also assessed using different electricity generation mixes based on the rated energy consumption, including charging losses, yielding operational emissions between 27.7 and 116.0 gCO2e/km. The findings demonstrate that the developed model provides realistic performance predictions and confirm the potential of BEVs to achieve high efficiency and substantially lower emissions than conventional passenger vehicles.

SIREN-Bench: Behavior-Driven Generation and Evaluation of Emergency-Vehicle Interactions

Emergency vehicles (EMVs) can reorganize surrounding traffic as civilian vehicles brake, change lanes, or form rescue corridors in response to their passage. Evaluating these safety-critical interactions requires behavior-level control over both EMV privileges and civilian responses, together with consistent sensing and ground truth. Existing datasets and simulation benchmarks do not directly provide this combination. We present \textbf{SIREN}, a behavior-driven SUMO--CARLA co-simulation platform for generating EMV--civilian interactions. SIREN couples SUMO's network-level traffic evolution and behavior logic with CARLA's continuous vehicle control and synchronized onboard sensing; depending on the active behavior, the interaction is controlled by SUMO, CARLA, or jointly. We instantiate the platform as \textbf{SIREN-Bench-v1}, comprising seven parameterized interaction templates across emergency levels L1--L3 and three behavior families, with synchronized sensor observations and simulator-native annotations. We demonstrate the benchmark through three representative tasks: 3D object detection, trajectory prediction, and vision-language risk understanding. Evaluations of nine trajectory predictors, four LiDAR-based detectors, and five vision-language models reveal behavior-dependent failure modes. Traffic-clearance interactions are hardest for detection, privileged intersection traversal is hardest for prediction, and no learned predictor outperforms the constant-velocity reference on average. Vision-language models perform substantially better on normal traffic than on near-miss and collision events. These results demonstrate the value of behavior-centered benchmarking and establish SIREN as an extensible data-generation and evaluation platform for autonomous-driving and transportation safety research.

ExplorIt: Simulation-based Fuzzing for Autonomous Driving Systems via Multi-Agent Interaction Modeling

Fuzzing-based simulation testing has become a fundamental technique for assessing the safety of autonomous driving systems (ADS). It operates by iteratively mutating simulation scenario configurations, scheduling scenario execution, and monitoring ADS-involved accidents. However, existing ADS fuzzers commonly rely on simplistic criticality metrics (e.g., inter-vehicle distance) for prioritizing critical scenarios during fuzzing, and lack deterministic guidance about how these heuristic-based critical scenarios should be further mutated to finally induce ADS-responsible accidents. Therefore, these existing fuzzers would inevitably miss truly critical driving scenarios or report various non-ADS-responsible accidents. To address these limitations, our key insight hints that EGO-to-NPC interactions (i.e., those recorded during the execution of a given scenario) offer comprehensive spatial-temporal information for reliable selection of critical scenarios and deterministic scenario mutation. Following this insight, we propose ExplorIt, a simulation-based ADS fuzzer enhanced with systematic formalization of interaction behaviors. Specifically, ExplorIt formalizes the runtime EGO-to-NPC interactions through drivable area estimation. That is, vehicles that share overlapped driving areas are considered to have interactive relationships. Under this modeling, ExplorIt can then deterministically mutate scenarios to curate more critical interactions by making EGO and NPC head for shared drivable areas. Extensive experiments on Apollo 8.0 demonstrate ExplorIt’s effectiveness, revealing 6.7 times more unique ADS-responsible accidents than baseline tools (i.e., DriveFuzz, SAMOTA, and AutoFuzz). Moreover, 83.2% of the reported accidents are ADS-responsible, compared to just 16.8% with baseline tools.

Introducing Complexity Metric for Test Scenarios for Automated Driving Systems