Hybrid Testing: A Vehicle-in-the-Loop Testing Method for the Development of Automated Driving Functions

Solmaz, Selim; Rudigier, Martin; Mischinger, Marlies; Reckenzaun, Jakob

doi:10.4271/12-04-01-0011

Cited by 8 publications

(7 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are some research efforts available to incorporate vehicle dynamics with pure traffic simulation to enhance fidelity and performance verification. Authors' of [50] proposed a co-simulation framework for development and performance verification of automated vehicles in critical scenarios using SUMO as traffic simulator and authors' of [51] proposed Hybrid testing which means evaluation of real vehicle in an enclosed ground using simulation scenario and sensor signals. Based on above, there are different ways to further expand this study, such as i) inclusion of more appropriate vehicle dynamics by considering lateral and longitudinal dynamics ii) controlling both acceleration/deceleration and steering angle iii) training on more realistic simulation environment and simulated sensor data for end-to-end training.…”

Section: Discussionmentioning

confidence: 99%

Safe Adaptive Deep Reinforcement Learning for Autonomous Driving in Urban Environments. Additional Filter? How and Where?

Alighanbari¹,

Azad

2021

IEEE Access

View full text Add to dashboard Cite

Autonomous driving (AD) provides a reliable solution for safe driving by replacing human drivers responsible for the majority of accidents. The emergence of Machine Learning, specifically Deep Reinforcement Learning (DRL), and its ability to solve complex games proved its potential to address AD challenges. However, model-free methods still suffer from safety-related issues that can be resolved using safe-DRL approaches. The addition of model-based safety filters to the learning-based algorithms provides safety bounds on their performance and constraint satisfaction. In this paper, we investigate the addition of a safety filter based on Model Predictive Control and show an increase in performance by 110% from -75 for Deep Deterministic Policy Gradient (DDP G) to 7.758. We study the impacts of safety filters (7.758 mean reward), heuristic rules, bounded additive noises (0.49% performance increase comparing to noisefree case), and exploration (3.425 mean reward) on the learning algorithm. We compare the effects of filters in the context of simulated exploration and bounded exploration and prove that bounded exploration results in 9.86% increase in mean reward and 12.95% decrease in std comparing to the other method. Additionally, inspired by Deep Internal Learning and biological mechanisms like brain plasticity, we investigate the idea of using each sample for training only once instead of utilizing stochastic batches which increases the mean testing accumulated reward by 1.87% and leads to the best performance (7.942 mean reward and 0.048 std). Finally, the results demonstrate better automotive results for our proposed method than DDPG. Our proposed method, DDPG with safety filter in bounded exploration and adaptive learning under noisy input conditions, has a success rate of 100% under different traffic densities for the simulation environment used in this paper and our assumptions. The proposed method's automotive results are shown for a braking scenario to avoid collision with other road users.

show abstract

Section: Discussionmentioning

confidence: 99%

Safe Adaptive Deep Reinforcement Learning for Autonomous Driving in Urban Environments. Additional Filter? How and Where?

Alighanbari¹,

Azad

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…This proposes an impossible task since the demonstration of the vehicle performance needs to be completed prior to the release for consumer use. Hence, reducing the development effort for ADAS functions and eventually enabling AD functions demand the extension of conventional test methods, e.g., physical test drives, with simulations in virtual test environments [4,12], or mixed methods combining the both testing abstraction levels [13][14][15][16].…”

Section: Virtual Testing Of Adas/ad Functionsmentioning

confidence: 99%

“…A previous example for this is from the EU/ECSEL project PRYSTINE, where robust multisensor fusion using additional sensor modalities was developed and demonstrated on an automated valet parking use case [48]. Another similar implementation was performed in the scope of the EU project INFRAMIX, where the focus was infrastructure-assisted ADAS implementations and C-ITS integration with the ADD vehicle [15].…”

Section: Test Setup and Measurement Hardwarementioning

confidence: 99%

Development and Experimental Validation of an Intelligent Camera Model for Automated Driving

Genser

Muckenhuber

Solmaz

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

The virtual testing and validation of advanced driver assistance system and automated driving (ADAS/AD) functions require efficient and realistic perception sensor models. In particular, the limitations and measurement errors of real perception sensors need to be simulated realistically in order to generate useful sensor data for the ADAS/AD function under test. In this paper, a novel sensor modeling approach for automotive perception sensors is introduced. The novel approach combines kernel density estimation with regression modeling and puts the main focus on the position measurement errors. The modeling approach is designed for any automotive perception sensor that provides position estimations at the object level. To demonstrate and evaluate the new approach, a common state-of-the-art automotive camera (Mobileye 630) was considered. Both sensor measurements (Mobileye position estimations) and ground-truth data (DGPS positions of all attending vehicles) were collected during a large measurement campaign on a Hungarian highway to support the development and experimental validation of the new approach. The quality of the model was tested and compared to reference measurements, leading to a pointwise position error of 9.60% in the lateral and 1.57% in the longitudinal direction. Additionally, the modeling of the natural scattering of the sensor model output was satisfying. In particular, the deviations of the position measurements were well modeled with this approach.

show abstract

“…However, it is important to note that this does not imply that everything is conducted solely in virtual environments. In fact, many approaches integrate both virtual and physical tests, and sometimes even hybrid testing methods [3,4].…”

Section: Introductionmentioning

confidence: 99%

Bayesian Gaussian Mixture Models for Enhanced Radar Sensor Modeling: A Data-Driven Approach towards Sensor Simulation for ADAS/AD Development

Walenta,

Genser,

Solmaz

2024

Sensors

Self Cite

View full text Add to dashboard Cite

In the realm of road safety and the evolution toward automated driving, Advanced Driver Assistance and Automated Driving (ADAS/AD) systems play a pivotal role. As the complexity of these systems grows, comprehensive testing becomes imperative, with virtual test environments becoming crucial, especially for handling diverse and challenging scenarios. Radar sensors are integral to ADAS/AD units and are known for their robust performance even in adverse conditions. However, accurately modeling the radar’s perception, particularly the radar cross-section (RCS), proves challenging. This paper adopts a data-driven approach, using Gaussian mixture models (GMMs) to model the radar’s perception for various vehicles and aspect angles. A Bayesian variational approach automatically infers model complexity. The model is expanded into a comprehensive radar sensor model based on object lists, incorporating occlusion effects and RCS-based detectability decisions. The model’s effectiveness is demonstrated through accurate reproduction of the RCS behavior and scatter point distribution. The full capabilities of the sensor model are demonstrated in different scenarios. The flexible and modular framework has proven apt for modeling specific aspects and allows for an easy model extension. Simultaneously, alongside model extension, more extensive validation is proposed to refine accuracy and broaden the model’s applicability.

show abstract

Hybrid Testing: A Vehicle-in-the-Loop Testing Method for the Development of Automated Driving Functions

Cited by 8 publications

References 0 publications

Safe Adaptive Deep Reinforcement Learning for Autonomous Driving in Urban Environments. Additional Filter? How and Where?

Safe Adaptive Deep Reinforcement Learning for Autonomous Driving in Urban Environments. Additional Filter? How and Where?

Development and Experimental Validation of an Intelligent Camera Model for Automated Driving

Bayesian Gaussian Mixture Models for Enhanced Radar Sensor Modeling: A Data-Driven Approach towards Sensor Simulation for ADAS/AD Development

Contact Info

Product

Resources

About