Search

The majority of technological processes include dynamic systems, which are characterized by structural and parameter uncertainty. Conventional control procedures based on such models are unlikely to produce the desired performance since deterministic models cannot appropriately characterize these uncertainties. When dealing with complex nonlinear systems that are characterized by ill-defined and unknown elements, fuzzy-logic based system is an effective method. Fuzzy controllers—whose rule basis is built on the expertise of human experts—are frequently utilized in this context to achieve desired performance. This knowledge might not be adequate for some complex processes, thus different methods for creating IF-THEN rules have been suggested. In this paper, the design of higher-order fuzzy sets is discussed and a generalized novel algorithm is developed for implementing type-n fuzzy sets and it is applied for controlling the angle of steering for a vehicle in such a way that the vehicle tracks the desired path. In the proposed methodology, fuzzification and defuzzification are taking place n number of times, and defuzzification of higher order fuzzy values up to type-1 fuzzy set is performed using the center of gravity method. The obtained type-1 fuzzy values are used in the rule base and inference mechanism for calculating the final crisp output. The significance of the present research is that the computation cost is not as high as expected because both fuzzification and defuzzification processes are recursive and the reduced new type-1 fuzzy values have the additional ability to model the uncertainty and vagueness as compared to normal type-1 fuzzy values. A comparison of the controllers based on the type of fuzzy sets is done based on the square of error (SE). Both the disturbance signal and uncertainty scenarios were also considered. The use of higher-order fuzzy sets facilitates the controller to give the more accurate results for controlling the vehicle and the corresponding simulation results suggest the same. [ABSTRACT FROM AUTHOR]

Steering angle controller is a core module of autonomous vehicles, where a slight miscalculation can cause severe accidents. Following safety precautions, development of robust and precise steering angle predictor is an active area of research. However, existing simulator based steering angle predictors lack in predictive performance and have not been evaluated on same benchmark datasets. Furthermore, most of them are evaluated on simulated datasets and their potential on real-world data as well as in cross-domain evaluation of both types data (real-world, simulated) remain unexplored. To accelerate and expedite research related to steering angle prediction contributions of this paper are manifold: 1) It presents two benchmark datasets that are developed using Udacity and CARLA simulators. 2) Following the need for comparative study, over both simulated datasets, it benchmarks the performance of existing predictors under 2 different evaluation settings namely: same-track and cross-track evaluation. 3) In cross-domain evaluation, it explores generalization potential of predictors by training predictors on simulated data and evaluating them on 2 real-world datasets and vice versa. 4) It presents a robust and precise steering angle predictor that utilizes skip connections for proper gradient flow among different convolutional layers. In same-track evaluation where predictors are trained and evaluated on same-track data, proposed predictor outperforms existing predictors by achieving least Mean Absolute Error (MAE) of 0.13, 0.19 and 0.065 over lake track, jungle track and CARLA based datasets, respectively. Similarly, in cross-track evaluation where predictors are trained on one track and are evaluated on other track data, once again proposed predictor outperforms existing predictors by producing average least MAE errors of 0.33 and 0.06 over Udacity and CARLA datasets, respectively. Over two real-world datasets, Sully Chen and Comma.ai, the proposed predictor demonstrates superior performance compared to existing simulator-based predictors, achieving the lowest MAE of 2.41 and 0.50, respectively.

The technology for determining the location of an object on the ground is the foundation for building vehicle navigation systems and surveillance systems after them. In general, such navigation systems make it possible to determine the coordinates of the vehicle's location and its directional angle, find the direction to the destination, and calculate the coordinates of observation objects. The technical implementation of systems can be quite diverse - from implementation on mechanical elements to their implementation using microelectronics elements. The main factors in the development of navigation systems are the transition to computer-integrated systems and resource-saving technologies. This will make it possible to increase the accuracy of navigation information, obtain a significant gain in the weight and size characteristics of the equipment, reduce its energy consumption and increase reliability. The possibility of modernization of odometrical navigation systems based on integrated computer technologies is considered. [ABSTRACT FROM AUTHOR]

The electro-hydraulic actuator (EHA) system applied in rear axle steering (RAS) is used to steer the rear auxiliary wheels of large commercial vehicles and prevent oversteering. For safety reasons, commercial vehicles reduce the steering angle as the load applied to the rear wheels increases or the speed of the vehicle increases. In this study, we present a well-composed model based design (MBD) of an RAS system employing EHA used in large commercial vehicles. In order to apply loads to the rear of the vehicle to validate the legitimacy of the modeling and to replace the actual model's experiments with the simulations, the rotational speed of the motor obtained in the experiment was input to the motor of the simulation model. The organized formulas of the steering angle based on the structural form were defined to compare the steering angle against both the cylinder displacement of the actual model and the simulated model. We also applied load working on the steering wheel to check the angle difference according to the weight. The organized formulas were applied in the MBD system to compare the results of simulation modeling with the actual experimental values to confirm the modeling's validity. [ABSTRACT FROM AUTHOR]

In this paper, the parameter optimization and error analysis of the rack and pinion steering mechanism are carried out on the basis of considering the influence of kingpin parameters. The steering characteristic equation describing the motion of the steering mechanism is calculated by analyzing the spatial geometrical relationship between the wheel and kingpin and unifying the projection relation between the kingpin and the equivalent steering trapezoid. The ideal Ackermann equation is modified by the Ackermann rate and the kingpin parameters. The modified Ackermann equation is used as the objective function. The segmented fitness function and the evaluation function with weighted factors are designed. A genetic algorithm containing the three functions is used to optimize the parameters of the steering characteristic equation. The error analysis of the numerical example shows that the accuracy of steering trapezoid structure parameters, steering characteristic equation, and Ackermann equation is improved compared with that before optimization. [ABSTRACT FROM AUTHOR]

A fully autonomous vehicle must ensure not only fully autonomous driving but also the safety and comfort of its passengers. However, the self-driving technology that is currently completed focuses only on perfect driving and does not guarantee the safety and comfort of passengers. This paper proposes a braking-pressure and driving-direction determination system (BDDS), which computes the brake pressure and steering angle optimized for passenger safety by utilizing more diverse information than existing autonomous vehicles. The BDDS proposed in this paper consists of two modules. The road roughness classification module (RRCM) classifies the roughness of the road by using the pressure data applied to the suspension and the K-NN algorithm and computes the optimal brake pressure. The passenger recognition and sharing module (PRSM) identifies the current occupant status of the vehicle by using a body pressure sensor and CNN, shares the information with surrounding vehicles, and computes the optimal steering angle using passenger information and road information. As a result of the simulations described in this paper, the parameters of AI models were optimized. In addition, the RRCS was about 7% more accurate than the K-means clustering algorithm, and PRS was about 9% more accurate than the existing seat recognition system. [ABSTRACT FROM AUTHOR]

Mobil listrik enggang evo3 merupakan salah satu mobil listrik Institut Teknologi Kalimantan (ITK) yang akan diikutkan pada kompetisi mobil listrik di Indonesia. Pengembangan mobil listrik terus dilakukan untuk memaksimalkan performa mobil. Permasalahan yang dihadapi oleh mobil listrik enggang evo3 adalah pada saat bergerak dengan dengan lintasan lurus, berbelok, atau slalom, mobil belum bisa mengikuti lintasan dengan baik. Sudut steer yang digunakan pada mobil enggang evo3 masih belum tepat untuk kondisi lintasan pada perlombaan. Sehingga,dilakukan penelitian tentang studi pengaruh sudut steer terhadap kecepatan lurus dan berbelok pada mobil listrik enggang evo 3. Tujuan dari penelitian ini adakah untuk mengetahui sudut belok mana yang terbaik pada kecepatan dan waktu tempuh mobil enggang evo 3 pada saat berbelok dengan radius belok lintasan yang sudah diketahui pada lintasan perlombaan. Variasi yang digunakan pada penelitian adalah sudut steer 200, 250, 300. Hasil dari penelitian menunjukan bahwa sudut steer terbaik untuk kecepatan dan waktu tempuh adalah sudut steer 20o dengan waktu tempuh 9,70 s dan kecepatan 29,66 km/h. karena semakin kecil sudut steer maka semakin besar kecepatan yang di hasilkan dan semakin besar kecepatan yang dihasilkan maka semakin singkat waktu tempuh yang diperlukan.

Control of pilotless electric vehicles indoors was studied. The issue of ensuring precise correspondence of control signals to the actual motion of transport vehicles in a room was examined. During the course of analyzing the dynamic model of the electric vehicle, it was discovered that the primary reasons for the occurrence of errors consists in the indirect nature of measuring the velocity of this vehicle by means of odometers. In order to solve this problem, it is proposed to use microwave Doppler sensors of the linear velocity of the wheels, observations of which do not depend on sliding, the mass of the electric vehicle, the voltage in the buses, and other parameters. Formulas were developed that make it possible, using the Doppler frequencies of sensors, to determine the current velocity and heading angle of electric vehicle control with the use of the Ackermann condition. Based on the specified formulas, a stable system for traffic control of pilotless transport electric vehicles on a specified route was developed. The proposed system can be used in the robotic transport systems. [ABSTRACT FROM AUTHOR]

This study presents smooth and fast feasible trajectory generation for autonomous driving vehicles subject to the vehicle physical constraints on the vehicle power, speed, acceleration as well as the hard limitations of the vehicle steering angle and the steering angular speed. This is due to the fact the vehicle speed and the vehicle steering angle are always in a strict relationship for safety purposes, depending on the real vehicle driving constraints, the environmental conditions, and the surrounding obstacles. Three different methods of the position quintic polynomial, speed quartic polynomial, and symmetric polynomial function for generating the vehicle trajectories are presented and illustrated with simulations. The optimal trajectory is selected according to three criteria: Smoother curve, smaller tracking error, and shorter distance. The outcomes of this paper can be used for generating online trajectories for autonomous driving vehicles and auto-parking systems. [ABSTRACT FROM AUTHOR]

This paper proposes an efficient path planning technique for the autonomous collision-free navigation of wheeled mobile robots with simple hardware based on an adaptive neuro-fuzzy inference system (ANFIS). The distance between the robot and obstacles is measured using three ultrasonic sensors that are installed on the left, front, and right of the robot. These distances from the sensors form the inputs to the ANFIS-utility function block that calculates an obstacle avoidance steering angle for the robot. The obstacle avoidance behavior of the robot is modeled under six scenarios of facing an obstacle. The instantaneous position of the robot and the target are available from Global Positioning System (GPS) modules. A simulation mobile robot in V-REP has been integrated into the ANFIS controller coded in MATLAB. The simulation results show that the proposed ANFIS-utility function-based path planning technique surpasses some of the related algorithms in terms of finding near-optimal paths.

A fully autonomous vehicle must ensure not only fully autonomous driving but also the safety and comfort of its passengers. However, the self-driving technology that is currently completed focuses only on perfect driving and does not guarantee the safety and comfort of passengers. This paper proposes a braking-pressure and driving-direction determination system (BDDS), which computes the brake pressure and steering angle optimized for passenger safety by utilizing more diverse information than existing autonomous vehicles. The BDDS proposed in this paper consists of two modules. The road roughness classification module (RRCM) classifies the roughness of the road by using the pressure data applied to the suspension and the K-NN algorithm and computes the optimal brake pressure. The passenger recognition and sharing module (PRSM) identifies the current occupant status of the vehicle by using a body pressure sensor and CNN, shares the information with surrounding vehicles, and computes the optimal steering angle using passenger information and road information. As a result of the simulations described in this paper, the parameters of AI models were optimized. In addition, the RRCS was about 7% more accurate than the K-means clustering algorithm, and PRS was about 9% more accurate than the existing seat recognition system.

Driver drowsiness is a factor in at least 20% of serious motor vehicle accidents. Although research has shown that Whole-Body Vibration (WBV) can induce drowsiness in drivers, it is unknown whether particular frequencies are more problematic. The present study systematically investigated the influence of WBV frequency on driver drowsiness. Fifteen participants each undertook six 1-h sessions of simulated driving while being subjected to WBV of either 0 Hz (no vibration), 1–4 Hz, 4–8 Hz, 8–16 Hz, 16–32 Hz or 32–64 Hz. Subjective sleepiness, as measured by the Karolinska Sleepiness Scale (KSS), confirmed that drivers felt drowsier when exposed to the two lowest frequency ranges (1–4 Hz and 4–8 Hz). Reaction time, which measures attention and alertness, was significantly impaired by the two lowest frequency ranges. Objective driving performance measures (Standard Deviation of Lane Position (SDLP), Standard Deviation of (SD) Steering Angle, Time in Unsafe Zone) also showed significant degradation due to exposure to the two lowest frequency ranges. Exposure to 1–4 Hz or 4–8 Hz vibration caused attention to become significantly impaired within 15–20 min and driving performance to be significantly impaired by 30–35 min. The other frequency ranges had little or no effect. These findings point to a need to develop equivalent vibration-induced drowsiness contours that can be adopted as transportation safety standards. • The effects of 60 min of whole-body vibration on reaction time, and driving performance were systematically examined. • Reaction times were significantly slowed after 15–20 min of exposure to 1–4 Hz and 4–8 Hz. • Driving metrics were significantly degraded after 30–35 min exposure to 1–4 Hz and 4–8 Hz. • Higher frequencies (8–64 Hz) had a minimal effect on drowsiness and driving performance. [ABSTRACT FROM AUTHOR]

This study presents smooth and fast feasible trajectory generation for autonomous driving vehicles subject to the vehicle physical constraints on the vehicle power, speed, acceleration as well as the hard limitations of the vehicle steering angle and the steering angular speed. This is due to the fact the vehicle speed and the vehicle steering angle are always in a strict relationship for safety purposes, depending on the real vehicle driving constraints, the environmental conditions, and the surrounding obstacles. Three different methods of the position quintic polynomial, speed quartic polynomial, and symmetric polynomial function for generating the vehicle trajectories are presented and illustrated with simulations. The optimal trajectory is selected according to three criteria: Smoother curve, smaller tracking error, and shorter distance. The outcomes of this paper can be used for generating online trajectories for autonomous driving vehicles and auto-parking systems.

• The Intelligent Transportation System (ITS) can assist the behavior driver on road, based vision sensor to monitoring steering angle actuator (steering wheel). • The duality between vision sensors and smart soft-sensors is very interesting in different embedded robotics systems. • This work provides a new approach to integrating smart soft sensors into ITS system. • The proposal smart soft sensor can be applied in smart cities. Sensors are considered as a great invention that radically contributed to saving time and effort for humans while moving or transporting things. That's the reason why, researchers are constantly working on a smart vision sensor that can provide important data such as directions, temperature, speed, risks... to drivers. Nowadays, there is a new tendance of smart cities that recommend the equipment of vehicles with sensors that can facilitate communication between all categories of vehicles. In this paper, we proposed an in-depth study for developing an assistance system that assists controls the vehicle position, managed a vision sensor (camera) that provides a perception of the road environment in real-time. Then to calculate the Steering Angle (SA), we use the Smart Soft-Sensors that take into consideration the road edges in the images. Each road image is identified by the SA, these images will be trained in a GPU processor using Nvidia's End to End architecture. Then an adaptive control by applications of the proposed system, gives SA estimated to assist in controlling the actuator (Steering Wheel). The results obtained by this approach encourage integrating it into automotive embedded systems to make the right behavior on the road. [ABSTRACT FROM AUTHOR]

This paper proposes an efficient path planning technique for the autonomous collision-free navigation of wheeled mobile robots with simple hardware based on an adaptive neuro-fuzzy inference system (ANFIS). The distance between the robot and obstacles is measured using three ultrasonic sensors that are installed on the left, front, and right of the robot. These distances from the sensors form the inputs to the ANFIS-utility function block that calculates an obstacle avoidance steering angle for the robot. The obstacle avoidance behavior of the robot is modeled under six scenarios of facing an obstacle. The instantaneous position of the robot and the target are available from Global Positioning System (GPS) modules. A simulation mobile robot in V-REP has been integrated into the ANFIS controller coded in MATLAB. The simulation results show that the proposed ANFIS-utility function-based path planning technique surpasses some of the related algorithms in terms of finding near-optimal paths. [ABSTRACT FROM AUTHOR]