Structural Design and Optimization of Commercial Vehicles Chassis under Multiple Load Cases and Constraints

De, Shuvodeep; Singh, Kamaldeep; Seo, Junhyeon; Kapania, Rakesh K.; Ostergaard, Erik; Angelini, Nicholas; Aguero, Raymond

doi:10.2514/6.2019-0705

Cited by 8 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• Multidisciplinary Design Optimisation: Multidisciplinary design optimization (MDO) is a research field that explores the use of numerical optimization methods to design engineering systems based on multiple disciplines, such as structural analysis, aerodynamics, materials science, and control systems. MDO is widely used to design automobiles, aircraft, ships, space vehicles, electro-chemical systems, and more, with the goal of improving performance while minimizing weight and cost [5][6][7][8][9][10][11][12][13]. With the advancement of computational power, MDO frameworks can also be used for autonomous vehicles to improve their structural design, aerodynamics, powertrain optimization, sensor integration and placement, path planning, control system optimization, and energy management.…”

Section: Of 29mentioning

confidence: 99%

“…also, the some parameters (θ) can be shared and optimized across all the tasks (θ sh ) and some parameters can be task-specific parameters (θ i ), which can in turn be shared and optimized among similar sub-tasks. Thus the objective function generalises to Equation (5). Choosing various task descriptor conditioning determines how these parameters are shared.…”

Section: Multi-task Learning and Meta Learningmentioning

confidence: 99%

See 1 more Smart Citation

Practical Autonomous Driving: A Survey of Challenges and Opportunities

De,

Saha,

Sallam

et al. 2023

Preprint

View full text Add to dashboard Cite

Autonomous Driving (AD) has become a prominent research area in the field of Artificial Intelligence (AI) and Machine Learning (ML) in recent years. This opens the door wider for self-driving cars to surpass conventional vehicles in the current market share. Despite its apparent simplicity, AD is composed of complex and heterogeneous systems, which are in need of a high level of coordination and alignment to ensure both full automation and safety. Therefore, numerous research studies have been conducted over the last few years to facilitate such coordination and accelerate the capacity of these types of vehicles to be self-managed in complex situations. The paper summarises these approaches that led to building what is known nowadays as the autonomous driving pipeline. Moreover, although skepticism exists regarding the practicality of AD as a viable alternative to traditional vehicles, extensive research suggests the multiple benefits of relying on them for mobility. While challenges remain in implementing AD in the real world, including regulation and technical issues, substantial progress in recent years indicates a growing acceptance of AD in the near future. This paper further explores the advantages and opportunities of the conducted such systems in facilitating the practicality of Autonomous Driving.

show abstract

Section: Of 29mentioning

confidence: 99%

Section: Multi-task Learning and Meta Learningmentioning

confidence: 99%

Practical Autonomous Driving: A Survey of Challenges and Opportunities

De,

Saha,

Sallam

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Other feature engineering methods like Attention mechanisms, for instance, Squeeze-and-Excitation (SE) [88] and Spatial Attention Module (SAM) [89], and other spatial mechanisms like Spatial Pyramid Pooling (SPP) [90] were proposed, where, information was aggregated from feature maps into a single dimension feature vector. Redmon et al [68] combined SPP with max-pooling output of kernel size k × k, k ∈ [1,5,9,13] and improved YOLOv3-608 AP 50 by 2.7% on the MS COCO dataset. Further, using RFB [91], it was improved to 5.7%.…”

Section: Research and Development In Ai And Control Strategies In The...mentioning

confidence: 99%

Practical Self-Driving Cars: Survey of the State-of-the-Art

Saha¹,

De²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Self-Driving Vehicles or Autonomous Driving (AD) have emerged as the prime field of research in Artificial Intelligence and Machine Learning of late. The indicated market share of existing vehicles might be supplanted by these self-driving vehicles within the next few decades. While AD may appear to be relatively easy, in fact, it is quite the contrary owing to involvement and coordination amongst various kinds of systems. Numerous research studies are being conducted at various stages of these AD systems. While some find the various stages of the AD Pipeline beneficial, others tend to rely on Computer Vision mostly. This paper attempts to summarise the recent developments in Autonomous Vehicle architecture. Although some people might seem to be sceptical about the pragmatic use of AD as an alternative to existing vehicles, the plethora of research and experiments being conducted suggests the opposite. Indeed, there are many challenges to implementing AD in the real world, but significant progress made in the last couple of years indicates general acceptance of AD in upcoming years.

show abstract

“…The previous one is a weaker variation of the DE/current-to-best/1 mutation, while the last one has shown promising execution in real parameter continuous optimization issues. The third mutation is a DE/weighted-randto-φbest operator (10). The three mutation strategies can be listed as below:…”

Section: A Imode Algorithmmentioning

confidence: 99%

Framework of Ensemble Parmeter Adapted Evolutionary Algorithm for Solving Constrained Optimization Problems

Saha¹,

De²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Real-world optimization problems are often governed by one or more constraints. Over the last few decades, extensive research has been performed in Constrained Optimization Problems (COPs) fueled by advances in computational intelligence. In particular, Evolutionary Algorithms (EAs) are a preferred tool for practitioners for solving these COPs within practicable time limits. We propose an ensemble of multi- method hybrid EA framework with four mutation operators, two crossover operators, multi-search [Differential Evolution (DE) & Gaining Sharing Knowledge (GSK)] optimization algorithm, and ensemble of constraint handling techniques to solve global real- world constrained optimization problem. The proposed frame- work FEPEA has an ascendancy of multiple adaptation strategies concerning the control parameters, search mechanisms, two sub-populations as well as uses knowledge sharing mechanism between junior and senior phases. The algorithm also combines the power of four popular constraint handling techniques (CHT) and uses a voting mechanism to select any particular CHT. On top of that, this algorithm also uses both linear and non- linear population size reduction in every step of the evolutionary process. We test our method on 57 real-world problems provided as part of the CEC 2020 special session & competition on real- world constrained optimization benchmark suite. Experimental results indicate that FEPEA is able to achieve state-of-the- art performance on real-world constrained global optimization when compared against other well-known real-world constrained optimizers.

show abstract

Structural Design and Optimization of Commercial Vehicles Chassis under Multiple Load Cases and Constraints

Cited by 8 publications

References 11 publications

Practical Autonomous Driving: A Survey of Challenges and Opportunities

Practical Autonomous Driving: A Survey of Challenges and Opportunities

Practical Self-Driving Cars: Survey of the State-of-the-Art

Framework of Ensemble Parmeter Adapted Evolutionary Algorithm for Solving Constrained Optimization Problems

Contact Info

Product

Resources

About