A systematic approach of vehicle plant model development for vehicle virtual testing &amp; calibration

Nese, Raghavendra; Pandey, Nabal Kishore; Thimmalapura, Satish

doi:10.1109/itec-india.2015.7386942

Cited by 4 publications

(2 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, we call a systematic abstraction of such system semantics and context the system model of such AD AI adversarial attacks. Specifically, in the AD context we identify 3 essential sub-components in such system model: 1) the AD system model, i.e., the fullstack AD system pipeline that encloses the attack-targeted AI components and closed-loop control, e.g., the object tracking, planning, and control pipeline for the object detection AI component; 2) the vehicle plant model [15,40], which defines the physical properties of the underlying vehicle system under control, e.g., maximum/minimum acceleration/deceleration, steering rates, sensor mounting positions, etc. ; and 3) the attack-targeted operation scenario model, which defines the physical driving environment setup, driving norms (e.g., traffic rules), and the systemlevel attack goal (e.g., vehicle collision, traffic rule violation, etc.)…”

Section: Related Work and Backgroundmentioning

confidence: 99%

A Survey on Physical Adversarial Attack in Computer Vision

Wang¹,

Wen²,

Jiang³

et al. 2023

Preprint

View full text Add to dashboard Cite

In the past decade, deep learning has dramatically changed the traditional hand-craft feature manner with strong feature learning capability, promoting the tremendous improvement of conventional tasks. However, deep neural networks (DNNs) have been demonstrated to be vulnerable to adversarial examples crafted by small noise, which is imperceptible to human observers but can make DNNs misbehave. Existing adversarial attacks can be divided into digital and physical adversarial attacks. The former is designed to pursue strong attack performance in lab environments while hardly remaining effective when applied to the physical world. In contrast, the latter focus on developing physical deployable attacks, which are more robust in complex physical environmental conditions (e.g., brightness, occlusion, etc.). Recently, with the increasing deployment of the DNN-based system in the real world, enhancing the robustness of these systems is an emergency, while exploring physical adversarial attacks exhaustly is the precondition. To this end, this paper reviews the development of physical adversarial attacks against DNN-based computer vision tasks (i.e., image recognition and object detection tasks), which can provide beneficial information for developing stronger physical adversarial attacks. For completeness, we also briefly introduce the works that do not involve physical attacks but are closely related to them. Specifically, we first proposed a taxonomy to summarize the current physical adversarial attacks. Then we briefly discuss the existing physical attacks and focus on the technique for improving the robustness of physical attacks under complex physical environmental conditions. Finally, we discuss the issues of the current physical adversarial attacks to be solved and give promising directions.

show abstract

Section: Related Work and Backgroundmentioning

confidence: 99%

A Survey on Physical Adversarial Attack in Computer Vision

Wang¹,

Wen²,

Jiang³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…As the market demand for new generations of electric and hybrid vehicle is more and more pressing International Energy Agency (2016), new challenges arise in the modelling branch (Soylu, 2011). Modelling process gives huge benefits in terms of prototyping costs and time and makes possible the parallelisation of the whole vehicle design process (Nese et al, 2015). In fact, it is a fundamental tool that can be used for many tasks spacing from the basic parameters definition to the development of noble and sophisticated control algorithms mainly aiming to improve the stability, the traction and the driving/braking torque split (Ivanov et al, 2015;Goodarzi and Esmailzadeh, 2007).…”

Section: Introductionmentioning

confidence: 99%

Lightweight dynamic vehicle models oriented to vehicle electrification

Dalboni

Mangoni

Lusignani³

et al. 2019

IJVP

View full text Add to dashboard Cite

The paper deals with the development of fast and lightweight vehicle dynamics models oriented to the vehicle electrification. Two models are created, as they are concerned with different accuracy levels. The first one is very essential: it consists of three dynamics, that is full vehicle, front wheels and rear wheels; regularised Coulomb friction model is adopted. The second model is more advanced since it comprehends the vertical dynamics due to the suspension system and tyre friction model comes from Pacejka's theory. The dynamics models are subsequently compared with a very sophisticated and accurate model developed thanks to Chrono::Engine (C::E): because C::E is a powerful and reliable software, this process can be considered as a first validation of the more essential vehicle descriptions. Afterwards, models are connected to an electric powertrain to evaluate the effects of the different mechanical models with respect to the same electric system; this also aims to estimate the characteristic quantities of the electric domain.

show abstract