CAIAS Simulator: Self-driving Vehicle Simulator for AI Research

Hossain, Sabir; Fayjie, Abdur Razzaq; Doukhi, Oualid; Lee, Deok Jin

doi:10.1007/978-3-030-00979-3_19

Cited by 17 publications

(10 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Schops et al [26], motivated by the limitations of existing multi-view stereo camera benchmarks (a stereo camera has two or more lenses, each with a separate image sensor: this allows the device to simulate binocular human vision and capture three-dimensional images [34]), introduce a new dataset and a technique to minimizes the photometric errors. In [32] a simulation environment is presented which includes the virtual structures of a car designed for autonomous driving tests; typical driving situations have been used to analyze how sensors respond when used in real circumstances as well as to confirm the impacts of environmental conditions. Considering instead sensor security issues, Petit et al [19] blind a commercial camera system used in commercial vehicles with several light sources.…”

Section: Related Workmentioning

confidence: 99%

RGB Cameras Failures and Their Effects in Autonomous Driving Applications

Secci

Ceccarelli

2023

IEEE Trans. Dependable and Secure Comput.

View full text Add to dashboard Cite

RGB cameras are one of the most relevant sensors for autonomous driving applications. It is undeniable that failures of vehicle cameras may compromise the autonomous driving task, possibly leading to unsafe behaviors when images that are subsequently processed by the driving system are altered. To support the definition of safe and robust vehicle architectures and intelligent systems, in this paper we define the failure modes of a vehicle camera, together with an analysis of effects and known mitigations. Further, we build a software library for the generation of the corresponding failed images, and we feed them to six object detectors for mono and stereo cameras and to the self-driving agent of an autonomous driving simulator. The resulting misbehaviors with respect to operating with clean images allow a better understanding of failures effects and the related safety risks in image-based applications.

show abstract

Section: Related Workmentioning

confidence: 99%

RGB Cameras Failures and Their Effects in Autonomous Driving Applications

Secci

Ceccarelli

2023

IEEE Trans. Dependable and Secure Comput.

View full text Add to dashboard Cite

show abstract

“…The study resulted in Model 3 being more robust than Nvidia's proposed CNN architecture model with lane keeping average time equals 617.3 seconds than Nvidia's 453.7 seconds. In [9], the authors upgraded a pre-existing Unity based self-driving simulator CAIAS using Blenders and SolidWorks, added features like RBG camera, Lidar Sensor and simulated a new environment having sorts of weather conditions including rain, snow, fog, autumn and lanes including muddy, forest, and regular. Implemented Nvidia's CNN model and scored behavior learning on parameters like obstacle avoidance, bumpy road tackle [1].…”

Section: Related Workmentioning

confidence: 99%

Deep Learning Implementation of Autonomous Driving using Ensemble-M in Simulated Environment

Gupta¹,

Upadhyay²,

Kumar³

et al. 2021

Preprint

View full text Add to dashboard Cite

Making Autonomous Driving a safe, feasible and better alternative is one the core problems the world is facing today. The horizon of the applications of AI and Deep Learning has changed the perspective of the human mind. Initially, what used to be thought as subtle impossible task is applicable today and that too in the feasibly efficient way. Computer vision tasks powered with highly tuned CNNs are outperforming humans in many fields. Introductory implementations of autonomous vehicle were merely achieved using raw image processing and hard programmed rule-based logic systems along with machine/deep Learning used as secondary objective handlers. With the autonomous driving method proposed by NVIDIA, the usability of CNNs is more adequate, adaptable and applicable. In this paper, we propose, the ensemble implementation of CNN based regression models for autonomous-driving. We have taken simulator generated driving view image dataset along with mapped file of steering angle in radians. After applying image pre-processing and augmentation, we have used two CNN models along with their ensemble and compared their performance as to minimize the risks of unsafe driving. We have compared Nvidia proposed CNN, MobileNet-V2 as regression model and Ensemble-M results for comparison their respective performance, MSE scores and compute time to process. In result analysis, the MobileNet-V2 model performs better in densely-featured roads and Nvidia model performs better in sparsely-featured roads whereas Ensemble-M normalizes the performance of both models and efficiently result in the least MSE score (0.0201) with highest computation time utilization.

show abstract

“…Behavioral simulations of CPS and IoT are increasing in their relevance with respect to analyzing reliability, because precise mathematical modeling is not straightforward [80]. These simulations are based on addressing four main topics: node localization, energy management, network multi-objective optimization, and self-capabilities approach [81,82].…”

Section: Cps-based Co-simulation Frameworkmentioning

confidence: 99%

Sensor Reliability in Cyber-Physical Systems Using Internet-of-Things Data: A Review and Case Study

et al. 2019

View full text Add to dashboard Cite

Nowadays, reliability of sensors is one of the most important challenges for widespread application of Internet-of-things data in key emerging fields such as the automotive and manufacturing sectors. This paper presents a brief review of the main research and innovation actions at the European level, as well as some on-going research related to sensor reliability in cyber-physical systems (CPS). The research reported in this paper is also focused on the design of a procedure for evaluating the reliability of Internet-of-Things sensors in a cyber-physical system. The results of a case study of sensor reliability assessment in an autonomous driving scenario for the automotive sector are also shown. A co-simulation framework is designed in order to enable real-time interaction between virtual and real sensors. The case study consists of an IoT LiDAR-based collaborative map in order to assess the CPS-based co-simulation framework. Specifically, the sensor chosen is the Ibeo Lux 4-layer LiDAR sensor with IoT added capabilities. The modeling library for predicting error with machine learning methods is implemented at a local level, and a self-learning-procedure for decision-making based on Q-learning runs at a global level. The study supporting the experimental evaluation of the co-simulation framework is presented using simulated and real data. The results demonstrate the effectiveness of the proposed method for increasing sensor reliability in cyber-physical systems using Internet-of-Things data.

show abstract

CAIAS Simulator: Self-driving Vehicle Simulator for AI Research

Cited by 17 publications

References 8 publications

RGB Cameras Failures and Their Effects in Autonomous Driving Applications

RGB Cameras Failures and Their Effects in Autonomous Driving Applications

Deep Learning Implementation of Autonomous Driving using Ensemble-M in Simulated Environment

Sensor Reliability in Cyber-Physical Systems Using Internet-of-Things Data: A Review and Case Study

Contact Info

Product

Resources

About