This paper presents the use of Google’s simultaneous localization and mapping (SLAM) technique, namely Cartographer, and adaptive multistage distance scheduler (AMDS) to improve the processing speed. This approach optimizes the processing speed of SLAM which is known to have performance degradation as the map grows due to a larger scan matcher. In this proposed work, the adaptive method was successfully tested in an actual vehicle to map roads in real time. The AMDS performs a local pose correction by controlling the LiDAR sensor scan range and scan matcher search window with the help of scheduling algorithms. The scheduling algorithms manage the SLAM that swaps between short and long distances during map data collection. As a result, the algorithms efficiently improved performance speed similar to short distance LiDAR scans while maintaining the accuracy of the full distance of LiDAR. By swapping the scan distance of the sensor, and adaptively limiting the search size of the scan matcher to handle difference scan sizes, the pose’s generation performance time is improved by approximately 16% as compared with a fixed scan distance, while maintaining similar accuracy.

This study introduces a novel platform to predict complex modulus variables as a function of the applied magnetic field and other imperative variables using machine learning. The complex modulus prediction of magnetorheological (MR) elastomers is a challenging process, attributable to the material’s highly nonlinear nature. This problem becomes apparent when considering various possible fabrication parameters. Furthermore, traditional parametric modeling methods are limited when applied to solve larger-scale cases involving large databases. Consequently, the application of non-parametric modeling such as machine learning has gained increasing attraction in recent years. Therefore, this work proposes a data-driven approach for predicting multiple input-dependent complex moduli using feedforward neural networks. Besides excitation frequency and magnetic flux density as operating conditions, the inputs consider compositions and curing conditions represented by magnetic particle weight percentage and the curing magnetic field, respectively. Extreme learning machines and artificial neural networks were used to train the models. The simulation results obtained at various curing conditions and other inputs confirm that the predicted complex modulus has high accuracy with an R² of about 0.997, as compared to the experimental results. Furthermore, the predicted complex modulus pattern and magnetorheological effect agree with the experimental data using both the learned and unlearned data.

In terms of vehicle dynamics, motion sickness (MS) occurs because of the large lateral acceleration produced by inappropriate wheel turning. In terms of passenger behavior, subjects experience MS because they normally tilt their heads towards the direction of lateral acceleration. Relating these viewpoints, the increment of MS originates from the large lateral acceleration produced by the inappropriate wheel’s turn, which then causes greater head movement with respect to the lateral acceleration direction. Therefore, this study proposes the utilization of fuzzy-proportional integral derivative (PID) controller for an MS minimization control structure, where the interaction of the lateral acceleration and head tilt concept is adopted to diminish the lateral acceleration. Here, the head movement is used as the controlled variable to compute the corrective wheel angle. The estimation of the head movement is carried out by an estimation model developed by the radial basis function neural network (RBFNN) method. An experiment involving a driving simulator was conducted, to verify the proposed control system’s performance in regard to the autonomous vehicle’s passengers. The results show that the averages of motion sickness incidence (MSI) index can be lowered by 3.95% for single lap and 11.49% for ten laps.

Magnetorheological (MR) fluid is among the smart materials that can change its default properties with the influence of a magnetic field. Typical application of an MR fluid based device involves an adjustable damper which is commercially known as an MR fluid damper. It is used in vibration control as an isolator in vehicles and civil engineering applications. As part of the device development process, proper understanding of the device properties is essential for reliable device performance analysis. This study introduce an accurate and fast prediction model to analyse the dynamic characteristics of the MR fluid damper. This study proposes a new modelling technique called Extreme Learning Machine (ELM) to predict the dynamic behaviour of an MR fluid damper hysteresis loop. This technique was adopted to overcome the limitations of the existing models using Artificial Neural Networks (ANNs). The results indicate that the ELM is extremely faster than ANN, with the capability to produce high accuracy prediction performance. Here, the hysteresis loop, which represents the relationship of force-displacement for the MR fluid damper, was modelled and compared using three different activation functions, namely, sine, sigmoid and hard limit. Based on the results, it was found that the prediction performance of ELM model using the sigmoid activation functions produced highest accuracy, and the lowest Root Mean Square Error (RMSE).

This paper aims to present a preliminary study of control reference parameters for stance assistance among different subjects and walking speeds using a passive-controlled ankle foot orthosis. Four young male able-bodied subjects with varying body mass indexes (23.842 ± 4.827) walked in three walking speeds of 1, 3, and 5 km/h. Two control references, average ankle torque (aMa), and ankle angular velocity (aω), which can be implemented using a magnetorheological brake, were measured. Regression analysis was conducted to identify suitable control references in the three different phases of the stance. The results showed that aω has greater correlation (p) with body mass index and walking speed compared to aMa in the whole stance phase (p1(aω) = 0.666 > p1(aMa) = 0.560, p2(aω) = 0.837 > p2(aMa) = 0.277, and p3(aω) = 0.839 > p3(aMa) = 0.369). The estimation standard error (Se) of the aMa was found to be generally higher than of aω (Se1(aMa) = 2.251 > Se1(aω) = 0.786, Se2(aMa) = 1.236 > Se2(aω) = 0.231, Se3(aMa) = 0.696 < Se3(aω) = 0.755). Future studies should perform aω estimation based on body mass index and walking speed, as suggested by the higher correlation and lower standard error as compared to aMa. The number of subjects and walking speed scenarios should also be increased to reduce the standard error of control reference parameters estimation.