Improvement of the Autodriver Algorithm for Autonomous Vehicles Using Roll Dynamics

To, Ching Nok; Milani, Sina; Marzbani, Hormoz; Jazar, Reza N.

doi:10.14669/am.vol91.art1

Cited by 3 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(5) Test metric minimal mean square error (MSE) is picked to compare all of the presented techniques. (6) The simulation results show that effectiveness of SCGNI soft computing is significantly superior than multi model filters for predicting the motion parameters of an underwater moving target.…”

Section: Introductionmentioning

confidence: 95%

“…State and measurement models use numerical expression to construct the present and observed dynamics of the turning target. The analysis of motion parameters including position, velocity, acceleration, turnover rate, direction and how these change from their existing points at run time are described by these mathematical expressions of dynamic object [6]. A single dynamic model in estimating motion parameters cannot accurately describe all of the unpredictable maneuvering behaviors of an underwater passive vehicle.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Scaled Conjugate Gradient Neural Intelligence for Motion Parameters Prediction of Markov Chain Underwater Maneuvering Target

Ali,

Zuberi,

Qing

et al. 2024

JMSE

View full text Add to dashboard Cite

This study proposes a novel application of neural computing based on deep learning for the real-time prediction of motion parameters for underwater maneuvering object. The intelligent strategy utilizes the capabilities of Scaled Conjugate Gradient Neural Intelligence (SCGNI) to estimate the dynamics of underwater target that adhere to discrete-time Markov chain. Following a state-space methodology in which target dynamics are combined with noisy passive bearings, nonlinear probabilistic computational algorithms are frequently used for motion parameters prediction applications in underwater acoustics. The precision and robustness of SCGNI are examined here for effective motion parameter prediction of a highly dynamic Markov chain underwater passive vehicle. For investigating the effectiveness of the soft computing strategy, a steady supervised maneuvering route of undersea passive object is designed. In the framework of bearings-only tracking technology, system modeling for parameters prediction is built, and the effectiveness of the SCGNI is examined in ideal and cluttered marine atmospheres simultaneously. The real-time location, velocity, and turn rate of dynamic target are analyzed for five distinct scenarios by varying the standard deviation of white Gaussian observed noise in the context of mean square error (MSE) between real and estimated values. For the given motion parameters prediction problem, sufficient Monte Carlo simulation results support SCGNI’s superiority over typical generalized pseudo-Bayesian filtering strategies such as Interacting Multiple Model Extended Kalman Filter (IMMEKF) and Interacting Multiple Model Unscented Kalman Filter (IMMUKF).

show abstract

Section: Introductionmentioning

confidence: 95%

Section: Introductionmentioning

confidence: 99%

Scaled Conjugate Gradient Neural Intelligence for Motion Parameters Prediction of Markov Chain Underwater Maneuvering Target

Ali,

Zuberi,

Qing

et al. 2024

JMSE

View full text Add to dashboard Cite

show abstract

“…data concerning the state of the electric batteries may be used to predict the range of the electric vehicle before it requires subsequent charging [1]. Semi-autonomous or fully autonomous electric vehicles are appearing on the roads more and more often [44].…”

Section: Introductionmentioning

confidence: 99%

Innovative approach to electric vehicle diagnostics

Małek

Taccani

2021

The Archives of Automotive Engineering – Archiwum Motoryzacji

View full text Add to dashboard Cite

Electromobility is associated with the ever faster development and introduction of new electric vehicles to the market. They use an electric motor to drive the wheels of the vehicle and the necessary electricity is stored in traction batteries. Electric vehicles have a different construction than traditional vehicles i.e. powered by internal combustion engines. For this reason, the manner of use, maintenance and service are different. Familiarization with selected operational issues of electric vehicles positively affects the reliability of their usage as well as safety and comfort of driving. An important component of electric vehicles is the traction battery. Its proper operation influences the long-term preservation of the initial energy capacity and, thus, the range of the vehicle. The article presents the tests of the state of traction batteries of a small electrically powered city vehicle. The vehicle, the batteries and the diagnostic devices used to assess the condition of the battery are described in detail. Based on the literature analysis and the observation of market trends, a fast and effective method of assessment of the technical condition of batteries in electric vehicles was proposed. The method has been tested on the selected vehicle. The technical condition of the battery in the vehicle was assessed after 4.5 years of operation and 30,000 km mileage.

show abstract

Simulation of Autonomous Mobility of Connected Vehicles in the Context of Real Conditions – a Case Study

Hanzl

Gross

Bartuška

et al. 2021

LOGI – Scientific Journal on Transport and Logistics

View full text Add to dashboard Cite

By designing road infrastructure, it is necessary to adapt the real situation to current development trends and respond accordingly to the intensity of traffic on the transport network. The development of the traffic situation is generally very dynamic, difficult to predict and influenced by a number of other factors. Modern technologies enable adaptive traffic flow management based on the sharing and evaluation of traffic information obtained in real time from traffic monitoring systems or even from vehicles as such (e.g. thanks to “Connected Vehicles” technology). The article first carries out a literature review of professional literature and scientific articles dealing with the issue of autonomous mobility and autonomous management of transport processes. That is followed by a description and creation of own algorithm for autonomous control of vehicles at the level crossing, including description of used data, methods and proposed solutions. Finally, the developed method (algorithm) is tested by the Anylogic simulation program in a real environment, as a case study of autonomous vehicle decision-making at the level crossing.

show abstract

Improvement of the Autodriver Algorithm for Autonomous Vehicles Using Roll Dynamics

Cited by 3 publications

References 13 publications

Scaled Conjugate Gradient Neural Intelligence for Motion Parameters Prediction of Markov Chain Underwater Maneuvering Target

Scaled Conjugate Gradient Neural Intelligence for Motion Parameters Prediction of Markov Chain Underwater Maneuvering Target

Innovative approach to electric vehicle diagnostics

Simulation of Autonomous Mobility of Connected Vehicles in the Context of Real Conditions – a Case Study

Contact Info

Product

Resources

About