An adaptive modified neural lateral-longitudinal control system for path following of autonomous vehicles

Tork, Nastaran; Amirkhani, Abdollah; Shokouhi, Shahriar B.

doi:10.1016/j.jestch.2020.12.004

Cited by 37 publications

(22 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A i ∈ ℜ n×n , B i ∈ ℜ n×m . The state matrix is derived from (15) which can be obtained by the input and output data [30], [31], or from the model which is linearized [32], [33].…”

Section: Lemmamentioning

confidence: 99%

“…In recent years, studies proposed numerous control strategies for the path tracking control, such as pure-pursuit control [4,5], sliding mode control (SMC) [6,7], model predictive control (MPC) [8,9], linear matrix inequality (LMI) methods [10,11], deep learning approaches [12,13] and other non-linear control methods [14,15]. Although the mentioned works have significant importance in both theoretical advancements and practical applications on path tracking for autonomous vehicles, it is worth noting that the obtained results still leave much to be desired.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Path tracking control for autonomous vehicles with saturated input: A fuzzy fixed‐time learning control approach

Zhang

Wang

Yang

et al. 2022

IET Intelligent Trans Sys

View full text Add to dashboard Cite

This paper presents a fuzzy fixed‐time learning path tracking control strategy for autonomous vehicles with saturated input and uncertainties. First, Takagi‐Sugeno (T‐S) model is designed to realize an accurate description of the nonlinear path tracking systems. The T‐S model is the weighted sum of a series of linear dynamics models. The weighting coefficients are described by fuzzy membership functions. Then, with the consideration of the saturated input, a fixed‐time learning control is proposed. It contains a learning law to estimate the uncertainties of the system on‐line. The fixed‐time convergence and the robustness properties are analyzed through Lyapunov stability theory. Finally, the effectiveness of the proposed control method has been verified through the CarSim/Simulink co‐simulations under different driving conditions. The results demonstrate that the developed controller significantly improves the performance of path tracking and follows the desired path well even in the case of parameter uncertainties and external disturbances.

show abstract

Section: Lemmamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Path tracking control for autonomous vehicles with saturated input: A fuzzy fixed‐time learning control approach

Zhang

Wang

Yang

et al. 2022

IET Intelligent Trans Sys

View full text Add to dashboard Cite

show abstract

“…It may be achieved by creating and implementing easy-to-use systems with the least amount of decision-making error. Driving task performance is one of the most critical AV components [44]. Therefore, it is imperative to present accurate, stable, and reliable navigation information to keep AVs safe [29].…”

Section: Perceived Safetymentioning

confidence: 99%

Do People Prefer Cars That People Don’t Drive? A Survey Study on Autonomous Vehicles

Meidutė‐Kavaliauskienė

Yıldız

Çiğdem

et al. 2021

Energies

View full text Add to dashboard Cite

Only recently, smart cities are taking shape, thanks to the rapid development of Internet of Things (IoT), cloud computing, and other similar technologies. Given the high demands placed on advanced technologies such as autonomous driving, cloud data services, and high-precision sensors, smart cities are creating an intelligent transportation environment conducive to the introduction of autonomous vehicles (AVs). In this context, the use of AVs in transportation is also considered a form of transportation innovation. As a result, AVs are considered more favorable to people interested in new technologies because they appear to be technologically superior. Their association with the most up-to-date technology can serve as a symbol for those who wish to demonstrate their interest in new technologies through their appearance. The positive image of technological innovation projected by AVs may influence their acceptance among technology enthusiasts to a significant degree. In this context, this study investigates the effects of perceived advantage, perceived risk, and perceived safety on the intention to use autonomous vehicles. For this purpose, data were collected from vehicle users living in Turkey by survey method. Secondly, factor analyses and regression analyses were performed with the data set obtained from 611 participants. As a result of the analyses, it has been determined that the perceived advantage and perceived security increase the intention to use autonomous vehicles. In contrast, the perceived risk reduces this intention to use. According to these results, recommendations were made to the companies about the level of acceptance of this technology by the users to assess their investments in autonomous vehicles better.

show abstract

“…Tork et al performed longitudinal-lateral dynamics control in an autonomous vehicle system. An adaptive neural network that is capable of producing nonlinear and complex mappings was designed [22]. Šabanovič developed a road type classification solution to improve vehicle dynamics control via the anti-lock braking system by estimating friction coefficient using video data and DNN algorithms [23].…”

Section: Introductionmentioning

confidence: 99%

Deep-Neural-Network-Based Modelling of Longitudinal-Lateral Dynamics to Predict the Vehicle States for Autonomous Driving

Nie

Min

Pan

et al. 2022

Sensors

View full text Add to dashboard Cite

Multibody models built in commercial software packages, e.g., ADAMS, can be used for accurate vehicle dynamics, but computational efficiency and numerical stability are very challenging in complex driving environments. These issues can be addressed by using data-driven models, owing to their robust generalization and computational speed. In this study, we develop a deep neural network (DNN) based model to predict longitudinal-lateral dynamics of an autonomous vehicle. Dynamic simulations of the autonomous vehicle are performed based on a semirecursive multibody method for data acquisition. The data are used to train and test the DNN model. The DNN inputs include the torque applied on wheels and the vehicle’s initial speed that imitates a double lane change maneuver. The DNN outputs include the longitudinal driving distance, the lateral driving distance, the final longitudinal velocities, the final lateral velocities, and the yaw angle. The predicted vehicle states based on the DNN model are compared with the multibody model results. The accuracy of the DNN model is investigated in detail in terms of error functions. The DNN model is verified within the framework of a commercial software package CarSim. The results demonstrate that the DNN model predicts accurate vehicle states in real time. It can be used for real-time simulation and preview control in autonomous vehicles for enhanced transportation safety.

show abstract

An adaptive modified neural lateral-longitudinal control system for path following of autonomous vehicles

Cited by 37 publications

References 38 publications

Path tracking control for autonomous vehicles with saturated input: A fuzzy fixed‐time learning control approach

Path tracking control for autonomous vehicles with saturated input: A fuzzy fixed‐time learning control approach

Do People Prefer Cars That People Don’t Drive? A Survey Study on Autonomous Vehicles

Deep-Neural-Network-Based Modelling of Longitudinal-Lateral Dynamics to Predict the Vehicle States for Autonomous Driving

Contact Info

Product

Resources

About