Search

In this study, the authors developed a novel active guidewire including a spiral-type magnetic microrobot and ball joint to realize active locomotion and improve the steering capability within external magnetic fields. Most active guidewires provide only steering ability without active locomotion, and their steering angles depend on the physical properties of the wire. The developed mechanism provides a wider range of steering angles because the total steering angle is the sum of the joint angle and wire angle. To evaluate the performance of the proposed mechanism, we compared and analyzed the steering and active locomotion in a dc field and rotating magnetic field in conditions involving and not involving the ball joint mechanisms. At a low magnetic field strength (up to 4 kA/m), considerable improvement in the steering angle owing to the use of the ball joint was noted. The dc and rotating fields with an intensity of 8 kA/m generated peak steering angles of 189° and 135°, respectively. Various experiments were conducted, and the results confirmed that the proposed mechanism could improve the steering ability while realizing active locomotion. In particular, the steering stability and movement ability corresponding to different types of magnetic fields could be analyzed.

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. Web of Science 13 1 art. no. 101491

Ultrasonic phased array technology has been widely used in the field of industrial nondestructive examination (NDE) but how to obtain the ideal results is still lacking. Based on Huygens’ principle, a one-dimensional ultrasonic phased array model was established to study the resultant sound field. Important parameters to the acoustic field characteristics of ultrasonic phased array were systematically investigated, such as the number of array elements, the working frequency, the focal length and the steering angle. Based on the simulation results, the optimal parameters can be obtained which can provide a theoretical basis for the actual application of ultrasonic phased array.

Safe driving and stable paths are essential for the autonomous vehicle navigation, that large and fast steering angle should be avoided. This paper addresses a local path generation problem for autonomous vehicles while the least maximum curvature and the shortest length are obtained with limited curvature rate. The properties of the novel feasible paths based on continuous curvature turns are investigated. And a simple and fast computational method is presented to solve the problem by iterative procedure. The simulation in this paper shows that, compared with recent researches, the performance of least maximum curvature and shortest length is obtained by the novel local path planner, and the driving behavior is closer to the human driver operation.

A novel solid-state Lidar is designed using two TE polarized beams counter-propagating towards each other. Two corresponding output beams can be seamlessly combined, doubling beam steering angle. A 28-degree beam steering range is achieved with a 100-nm wavelength tuning.

A Deep Neural Network (DNN) model is used to perform intelligent, safety-critical tasks in Autonomous Driving Systems (ADS). In our prior work, we proposed a combinatorial testing approach to test DNN models used to predict a car's steering angle. We generate test images by applying a set of combinations of basic image transformations. In this paper, we report a preliminary study that compares the performance of synthetic images generated using a combinatorial approach to DeepTest, a state-of-the-art tool that aims at generating test inputs that maximize neuron coverage. We present an experimental evaluation by measuring and comparing the neuron coverage achieved using the two approaches. Two pre-trained DNN models from the Udacity driving challenge are used as the subject DNNs. The results suggest that the combinatorial approach performs better than the DeepTest approach in generating valid synthetic images and covering an additional number of neurons.

Human drivers have complex and unique driving characteristics, even when driving in common, well-defined scenarios such as lane changes. In this study, we propose using probabilistic, deep generative models to predict personalized driving behavior including velocity, acceleration, and steering angle sequence. Probabilistic approaches are applied to model uncertainty in the driving behavior of individual drivers as a distribution, while surrounding vehicle and driver ID information are considered as given conditions in the distribution. We train individual driver models using real-world driving data, and use them to predict sequences of future driving behavior in dynamic environments, using historical data to take personal driving styles into account. Our results show that the proposed driver behavior modeling method is able to learn from a driver's vehicle operation data and their interactions with surrounding vehicles to reproduce their specific driving style.

Nowadays unmanned surface vessel (USV) automatic collision avoidance technology in a dynamic environment is getting increasingly concern in the intelligent navigation field. And taking USV's dynamic characteristics, COLREGs (International Regulations for Avoiding Collisions at sea), and the complexity of the marine environment into account is a trend of USV automatic collision avoidance technology. Based on the traditional potential field approach and COLREGs, this improved potential field model designed the collision avoidance algorithm integrated with rules, considered collision action timing, steering angle amplitude, and resume timing. More actually, the novel algorithm divided the collision avoidance process into three stages: track keeping, collision avoidance, and course resumption. At last, the simulation results show the feasibility and availability of collision avoidance.

In recent years, autonomous navigation of ships has become a hot research area in shipping industry. There is no doubt that safe collision avoidance is an important part of ship autonomous navigation. To improve safety and economy of ship in the process of ship collision avoidance, this paper proposed a path planning method for ship collision avoidance based on heuristic algorithm. In that, the sailing distance and the altering angle as genetic gene construct ship path of collision avoidance. Experimentally, stochastic schemata exploiter (SSE) and genetic algorithm (GA) and were employed as optimization method to verify the feasibility of the proposed path planning method. The optimal ship collision avoidance path can be obtained. Compared with previous research, the accuracy of ship path planning was improved from 1 degree, 0.25 nautical miles to 0.1degree, 0.1 nautical mile for ship steering angle and ship navigation distance. The main contribution of this paper is that the accuracy problem of ship path planning is considered and one ship path planning method is proposed to improve accuracy of ship collision avoidance path planning.

Cycling is a travel mode that offers great advantages in terms of space consumption, health and environmental sustainability, and this makes it particularly popular in cities. However, it is also plagued by a poor road safety record, which has yet to be properly addressed due to a prevailing lack of understanding of the behavioral traits of cyclists that would enable the design of suitable interventions. The aim of this study is to offer some insight into cyclist behavior by investigating its relation with the road environment, as expressed by real-world cyclist trajectories in urban areas. Using an instrumented bicycle, quantitative measurements in terms of speed, steering angle and roll angle in response to different highway features were taken from cyclists riding along a pre-determined route in the city of Southampton, UK. The data were analyzed using neural networks and multiple linear regression and the findings highlighted a number of significant positive and negative effects for policy-makers and stakeholders to consider in the design of cyclist facilities and road infrastructure in general, as well as in road user education.

This paper proposes a single-input single-output (SISO) digital predistortion (DPD) model for linearizing millimeter-wave (mm-wave) RF beamforming arrays. It starts with a dual-input power amplifier (PA) model that accounts for steering angle-dependent load modulation effects. This dual-input model is then transformed into a SISO model under the assumption of weak PA nonlinearity and RF beamforming architecture. The underlying coefficients of the SISO array model incorporate the beamforming weights, antenna cross-coupling, channel coefficients, and any possible phase-shifter gain variation with phase shift setting. An over-the-air (OTA) measurement setup is finally developed to validate the capacity of a SISO DPD model to linearize two different arrays-under-test with 4 and 64 elements and radiating mm-wave modulated signals with 320- and 800-MHz bandwidth. Although, in principle, the DPD coefficients should be retrained for each steering angle, experimental results have shown that the same set of coefficients can be used over a wide range of steering angles, and only a few sets of trained DPD coefficients are sufficient to minimize the distortion in a mm-wave RF beamforming array across a 120° steering range.

Steering angle and driving force saturations are inevitable in autonomous vehicle motions, which will degrade the motion control performance and even deteriorate the driving safety. In addition, the strong coupling of lateral and longitudinal motions of autonomous vehicles also contributes to the saturations damage and increases the control difficulty. To reduce these negative impacts on motion control, a novel motion controller for automated vehicles is presented in this paper. Firstly, an extended 3 degree of freedom vehicle dynamic model is built with the unknown saturations, strong-coupled motion characteristics and external disturbance considered simultaneously. Then, a coordinated controller is designed to complete motion control task based on sliding-mode control (SMC) and non-singular fast terminal sliding-mode control (NFTSM). Moreover, a three-layer radial basis function neural network (RBFNN) is adopted as a compensator to approximate modelling uncertainties. Based on Lyapunov stability theory, the uniform ultimate boundednesses of motion control errors are guaranteed. Simulation results show that the proposed controller owns smaller steady-state errors and faster convergence speed.

Self driving vehicle is a vehicle that can drive by itself it means without human interaction . This system shows how the computer can learn and the over the art of driving using machine learning techniques. Therefore for a car achieving the autonomous ability it must show the control of human activities while driving. Those activities include control of steering wheel. There exist different techniques to control the steering angle and one of them is CNN. In this article we are going to see how CNN can be used to predict the steering angle.

The Steer-by-Wire (SbW) system is probably the most significant innovation among drive-by-Wire technologies in the automotive industry. Without the mechanical link, the most challenging issue is to control the wheels to closely follow the driver’s command. To improve the robustness of the model predictive control (MPC) in the presence of modeling uncertainties and disturbances in the steering control processes, a sliding mode predictive tracking control (SMPC) strategy for a SbW system with uncertain dynamics is proposed. The simulation and experimental results demonstrate that the performance of the proposed SMPC tracking controller is superior to both SMC and MPC methods for the steering angle tracking task.

Tire wear and overuse are serious issues for four-in-wheel-motor-driven electric vehicles (FIWMD EVs). As a result, this paper proposes a hierarchical control framework to improve the safety of FIWMD EVs while save the tire slip energy (i.e. reduce the tire wear), which includes a linear quadratic regulator (LQR) in the outer layer and a holistic corner controller (HCC) in the inner layer. The LQR can highly improve the lateral stability of the vehicles under extreme conditions by producing an additional yaw moment and a front wheel steering angle. Whereas, the HCC can efficiently distribute the deviation of the longitudinal force and the additional yaw moment by a step-ahead prediction. In this framework, to reduce the tire slip energy, a semi-empirical tire slip energy model is developed and used for tuning the HCC controller. In this way, not only the lateral stability of such EVs can be ensured but also the tire slip energy can be reduced. More importantly, this paper compares the lateral stability and slip energy of the vehicle under lane change condition between four methods – without control, traditional axis distribution, tire workload usage and tire slip energy. The results demonstrate that the proposed controller presents an excellent control capability. In addition, different from the widely used axis load distribution, the longitudinal velocity of the proposed method is more stable. More importantly, the tire slip power and energy are much smaller than others. It achieves 16.62% reduction of the tire slip energy.

Recently, dual-motor driving steer-by-wire (SbW) systems have been introduced and have received considerable attention because they can overcome the limitations of single motor driving SbW systems, which cannot provide large torques required by commercial vehicles and are vulnerable to faults. The two main issues on the performance of the dual-motor driving SbW systems is to ensure steering robustness against model uncertainties, external disturbances, and road condition changes and to synchronize the steering angle. In this paper, a sliding mode controller (SMC) with a disturbance observer (DOB) under master-slave control is proposed to tackle these issues. The combination of an SMC and a DOB is employed to guarantee strong robustness against model uncertainties and external disturbances. In addition, master-slave control is applied to enhance the synchronization performance of dual motor driving SbW systems with significantly different dynamic and response characteristics. Comparative experimental studies are conducted to verify the excellent performance of the proposed control scheme for dual-motor driving SbW systems.

In this paper, a monocular camera-based method is proposed to estimate the steering angle in autonomous driving. A second-order particle filtering algorithm is used to estimate the steering angles. The filtering algorithm is modeled at the scene-level for varying driving patterns. For a given road scene, individual proposal and likelihood distributions are modeled with deep learning-based regression frameworks for normal driving and obstacle avoidance driving patterns, respectively, the proposal distribution is modeled using a novel long short-term memory-based mixture-of-expert; and the likelihood is modeled using a convolutional neural network. To estimate the driving pattern captured from the monocular camera, a long recurrent convolutional network is adopted and trained. By modeling the distribution at the scene-level for different driving patterns, we accurately model the particle filter distributions. Consequently, for autonomous driving, the steering angle is robustly estimated with few particles. The proposed framework is validated on multiple acquired sequences. A detailed comparative and parametric analysis of the algorithm is performed. The experimental results demonstrate the robustness and accuracy of our filtering algorithm for varying road scenes and driving behaviors.

This paper discusses research to control the steering wheel angle of an All-Terrain Vehicle (ATV) in a forest environment using machine learning techniques and a camera feed. The research uses different semantic segmentation (S.S.) techniques to analyze visual data gathered from the ATV driven in the forest. It then uses different linear regression models to find the best suited model to predict the steering wheel angle. This paper discusses the data gathering process for the visual data and steering wheel angles. It also discusses the data preparation for the S.S. models and the S.S. models used. Then it presents the data preparation for the linear regression models used after the S.S‥ Finally, the training and usage of the different linear regression models, the final results, and conclusions are represented. All models were computed offline on a Jetson Nano Nvidia GPU. Our objective is to find the best model which will allow the vehicle to drive in real-time in future trials.

Optical phased array is an important device for beam steering. To achieve the optical phased array which has wide steering angle, it is necessary the narrow antenna pitch. In this report, we proposed and investigated numerically the plasmonic waveguides antenna which has the low crosstalk for wide steering angle in the optical phased array. It was found that the crosstalk at the antenna pitch 800 nm of the gap type plasmonic waveguide can be almost ignored by the numerical simulation. The steering angle 156 degrees much wider than that of the conventional waveguides was achieved at this antenna pitch.

In an automated steering system of the self-driving vehicles, the steering wheel angle is measured by the absolute angular displacement sensors or relative angle sensors. However, these sensors either encompass global navigation satellite systems (GNSS)/gyroscope – Micro Electromechanical-Sensor (MEMS) based solutions or comprise of the complex gear-based mechanical structure which results in latency and additive bias in the accumulative steering angle assessment. To address these issues, we propose a novel steering angle assessment system based on enhanced gear mechanism along with the adapted rotation paradigm for the customized self-driving vehicles. Additionally, a digital signal processing system has been introduced to resolve the issues in the identification of absolute central and max-bounding steering wheels position in self-driving vehicles. In assistance with the proposed mechanism, an algorithm has also been proposed to optimize the computed steering angle to minimalize the effect of additive bias in the accuracy. The proposed mechanism has been installed in the customized self-driving testbed vehicle and rigor validation has been performed in the straight and curvy road scenarios. Finally, the comparison study has been carried out between the conventional relative sensor and the proposed mechanism to show the accuracy and effectiveness of the proposed mechanism in terms of error rate, stability, and deviation.

In order to improve the vehicle handling performance and lateral stability, an integration of Active Front Steering Control (AFS) and Direct Yaw Moment Control (DYC) has been investegated. Model Predictive Controller (MPC) has been formulated for integrated AFS and DYC. The driver steer angle has been treated as a desired steering command and MPC controller is designed to calculate optimal steer angle and the amount of brakes by considering steering angle constraints and driver's steer angle. To design more effective control scheme, different road conditions like slippery, rough and normal, have been considered. In these situations vehicle's tires road adhesion coeficients (µ) varies. The proposed work treats variation of adhesion coefficients as parameter uncertainty and Optimal Guaranted Cost Controller (OGCC) used to handle this uncertainity. So in the proposed work both MPC and OGCC work in coordination to calculate the suitable steer angle and optimal brakes so that the best possible responce can be achieved. Different simulations have been performed in order to verify the effectivness of proposed controller. Simulation results of the proposed control scheme have also been compared with the results of different control stratigies.

In this work, an algorithm of machine learning for self-driving car using udacity and unity self-driving car simulation software has been presented. Using the software, the car is driven on the simulated circuit having three cameras mounted on car hood which generate three images simultaneously and acceleration and de-acceleration of the car steering angle and brake. This method includes a behavior cloning approach and tries to replicate a behavior of human driver. For training the model, approximately, 18,000 training samples are required, and by using image augmentation technique, an increase in the data sample with few times is obtained, which leads to little robust simulated self-driving car.

Driving fatigue is a physiological phenomenon that often occurs during driving. When the driver enters a fatigue state, they will become distracted and unresponsive, which can easily lead to traffic accidents. The driving fatigue detection method based on a single information source has poor stability in a specific driving environment and has great limitations. This work helps with being able to judge the fatigue state of the driver more comprehensively and achieving a higher accuracy rate of driving fatigue detection. This work mainly introduces research into different signal fusion methods to detect fatigue drive. This work will take the normal driver’s breathing signal, eye signals, and steering wheel signal as research objects and collect and isolate the characteristics of the fatigue detection signal. Research was then conducted on different signal fusion methods for the detected depth of breath. Change of steering angle, eyelid closure, and blinking marks and the fatigue driving experiment was designed to evaluate the results of different data fusion methods. Experimental results show that the detection accuracy of the heterogeneous signal fusion method in fatigue detection is as high as 80%.

Developing an intelligence system to automatically turn ON or OFF the indicator in automotive (particularly four wheeler) by drawing input from sensors. Almost 50% of drivers failing to use indicators while changing lanes or overtake a vehicle. This leads to vehicle accidents and may cause some serious issues. The proposed system comprises of a steering angle sensor, optical sensor for vehicle detecting and tracking and also incorporates open CV (AI tool) for lane detection and this system is adaptable to the current situation.

In this paper three types of Silicon Photonics OPA architectures are proposed and investigated. Edge-fire optical phased array, that simplifies the design of the OPA. Second architecture is OPA with grating coupler antennas. Maximum steering angle for edge-fire OPA is ±44°, FWHM is 0.10986°. For GC OPA steering angle is ±20° and FWHM=1.003116°. Third architecture is the Slanted Grating Coupler with a FOV of 100°.

The emergence of autonomous cars in today’s world makes it imperative to develop superlative steering algorithms. Deep convolutional neural networks are widely adopted in vision problems for their adept nature to classify images. End-to-end models have acted as an excellent substitute for handcrafted feature extraction. This chapter’s proposed system, which comprises of steering angle prediction, road detection, road centering, and object detection, is a facilitated version of an autonomous steering system over just considering a single-blind end-to-end architecture. The benefits of proposing such an algorithm for the makeover of existing cars include reduced costs, increased safety, and increased mobility.

This research has done a thorough literature review about the vehicle collision warning/avoidance system and a system model is represented using Matlab. Two specific scenarios are modeled here–90 degrees left turning and lane-change maneuver. Based on these two scenarios, the vehicle’s performance is analyzed in terms of its steering angle and sideslip. In addition, the animation is also provided

In order to solve the problems of low efficiency, large blind area, and the problem that glass size affects wiping efficiency and blind area, we propose a square wave wiping path, and propose a robot structure suitable for square wave path motion. The relationship between wiping efficiency and wiping blind area of Z-shaped path and boundary triangle path and the glass size and steering angle are analyzed in detail. The wiping efficiency and wiping blind area are contradictory under these two paths. In addition to the structure blind area caused by the robot's own structure, the wiping blind area of square wave path is 0, which is not affected by glass size. Set the size of the glass turning angle, in the ideal situation, compared the three ways of wiping blind area, wiping efficiency, square wave path wiping blind area is smaller than the others , and the square wave path reaches the ideal blind area level. The square wave path proposed in this paper can effectively solve the contradiction between wiping efficiency and wiping blind zone.

In the path tracking algorithm of unmanned vehicles, pure pursuit algorithm is widely used in low-speed application scenarios because of its simple model and easy implementation. In the pure pursuit algorithm, it is difficult to choose a suitable look-ahead distance for the unmanned vehicle. And there is a problem of outputting discontinuous steering angle under two continuous control cycle. Therefore, large heading and lateral error exist and make the tracking unstable. To solve these problems, firstly the look-ahead distance can be calculated by using the vehicle speed and the path information. Secondly, the PID controller is used to optimize the target steering angle which is calculated by the pure pursuit algorithm and then output stable angle to implement path tracking. In the golf course environment, a golf unmanned vehicle is used to track the predefined path. The results of optimized method show that the lateral error is reduced by 15.13 cm and the heading angle error is reduced by 1.88 degrees.

This paper addresses an active probing signal-based attack detection method for autonomous vehicular systems. Employing active probing signals for attack detection may become a common method for detecting replay attacks performed using prerecorded sensor data. Conventional replay attack detection methods usually operate by injecting active probing signals into the control inputs and simultaneously checking whether the effect appears on the output signals. When active probing signals are used in vehicular systems, they may change the vehicle acceleration and steering angle. The tracking performance can degrade; inspired by this issue, we develop an attack detection method employing disturbance observers. The attack detection method compensates for the effect of active probing signals and detects malicious attacks, including replay attacks. To validate the effectiveness of the proposed method, several simulations are carried out.

In this paper, we design an automatic parking system based on roadside vision, computing and Vehicle-to-Road (V2R) network. We use ArUco marker and roadside cameras to establish the garage coordinate system and obtain the position of the intelligent vehicle. The parking reference trajectory from the entrance to available parking space is planned by the roadside computer according to the parking request. To tracking the parking reference trajectory, we utilize an increment P control and the pure pursuit algorithm, which are used to control the longitudinal speed and the steering angle, respectively. The control laws are calculated in the roadside computer, and then sent to the vehicle through the V2R network. The proposed method reduces the cost of intelligent hardwares equipped in the vehicles, and saves the time spent on looking for an available parking space. We implement this automatic parking system on a platform containing miniaturized vehicles and roadside equipments. Experimental results show that the parking system we design can achieve the required parking goal.

Estimating the steering angle is a fundamental but challenging problem for autonomous vehicles. The main challenges come from different road conditions and capturing sensors. In this paper, we first present an autonomous vehicle prototype for different tasks in small and narrow indoor environment. We then perform a comparative study on two approaches for vision based steering angle estimation to drive the designed vehicle. One approach bases on conventional image processing techniques such as edge detection and Hough transform while the other one bases on advanced deep learning (convolutional neural network). We evaluate both methods on a common dataset. Experimental results show that in the scenario with simple and static background, image processing techniques give lightly faster and more precise steering angle. However, deep learning based approach is well generalized to background changes. We applied and integrated our proposed methods on the designed vehicle and show their capacity to drive the vehicle accurately.

Despite the sophisticated technology that could prevent accidents of vehicles on highways, many lives are claimed due to the drowsiness of drivers. According to the data reported by the NHTSA (National Highway Traffic Safety Administration) of USA, 846 succumb to death and it has become a major threat these days which is evident from 83,000 cases registered due to drowsy driving. Drowsiness is the feeling of being sleepy or being inactive towards activities and this causes a sleeping sensation which leads to closure of eyelids while driving resulting in major accidents. There are systems in action that could detect physical awaken of the driver, but detecting the drowsiness and deviation of the driver is a challenging problem in the field of transportation. Many factors could influence the drivers to fall asleep during their journeys and the chances of getting drowsy increases in night times than in the dawn and journeys did alone are even more dangerous. So, we introduce a system which is capable of monitoring the person’s consciousness, acceleration pattern and the angle of vehicle’s steering simultaneously to detect the deviation and drowsiness of the driver. The process of drowsiness and deviation detection of the driver has been done using image processing techniques. Our proposed system alerts the driver by comparing the acceleration pattern to the Eye Aspect Ratio (EAR) for drowsiness. It also monitors his facial movements, changes in steering angle to detect the deviation.