scholarly journals Effect of Various Activation Function on Steering Angle Prediction in CNN based Autonomous Vehicle System

2019 ◽  
Vol 9 (2) ◽  
pp. 3806-3811
Keyword(s):  
Object Detection ◽  
Autonomous Vehicle ◽  
Activation Function ◽  
Steering Wheel ◽  
Main Mode ◽  
Steering Angle ◽  
The Road ◽  
Human Agent ◽  
Cloning Method ◽  
Almost All

Autonomous or Self-driving vehicles are set to become the main mode of transportation for future generations. They are highly reliable, very safe and always improving as they never stop learning. There are numerous systems being developed currently based on various techniques like behavioural cloning and reinforcement learning. Almost all these systems work in a similar way, that is, the agent (vehicle) is completely aware of its immediate surroundings and takes future decisions based on its own historical experiences. The proposed work involves the design and implementation of Convolutional Neural Network (CNN) enhanced with new activation function. The proposed CNN is trained to take a picture of the road in front of it as input and give the required angle of tilt of the steering wheel . The model is trained using the behavioural cloning method and thus learns to navigate from the experiences of a human agent. This method is very accurate and efficient. In this paper, for the detection of object and vehicle in autonomous vehicle, the existing Tensorflow object Detection API is collaborated with pretrained SSD MobileNet model. This paper presents in detail literature survey on various techniques that have been used in predicting steering angle and object detection in self driving car. Apart from that, the effect of activation functions like ReLU, Sigmoid and ELU over the CNN model is analysed.

Vision-Based Navigation of Autonomous Vehicles in Roadway Environments with Unexpected Hazards

2019 ◽  
Vol 2673 (12) ◽  
pp. 494-507 ◽  
Author(s):  
Mhafuzul Islam ◽  
Mashrur Chowdhury ◽  
Hongda Li ◽  
Hongxin Hu
Keyword(s):  
Object Detection ◽  
Autonomous Vehicles ◽  
Autonomous Vehicle ◽  
Semantic Segmentation ◽  
Steering Wheel ◽  
Potential Hazard ◽  
Driving System ◽  
Hazardous Object ◽  
Vision Based Navigation ◽  
Navigational System

Vision-based navigation of autonomous vehicles primarily depends on the deep neural network (DNN) based systems in which the controller obtains input from sensors/detectors, such as cameras, and produces a vehicle control output, such as a steering wheel angle to navigate the vehicle safely in a roadway traffic environment. Typically, these DNN-based systems in the autonomous vehicle are trained through supervised learning; however, recent studies show that a trained DNN-based system can be compromised by perturbation or adverse inputs. Similarly, this perturbation can be introduced into the DNN-based systems of autonomous vehicles by unexpected roadway hazards, such as debris or roadblocks. In this study, we first introduce a hazardous roadway environment that can compromise the DNN-based navigational system of an autonomous vehicle, and produce an incorrect steering wheel angle, which could cause crashes resulting in fatality or injury. Then, we develop a DNN-based autonomous vehicle driving system using object detection and semantic segmentation to mitigate the adverse effect of this type of hazard, which helps the autonomous vehicle to navigate safely around such hazards. We find that our developed DNN-based autonomous vehicle driving system, including hazardous object detection and semantic segmentation, improves the navigational ability of an autonomous vehicle to avoid a potential hazard by 21% compared with the traditional DNN-based autonomous vehicle driving system.

Autonomous vehicle path tracking control considering the stability under lane change

2021 ◽  
pp. 095965182199135
Author(s):  
Xiaolong Chen ◽  
Bing Zhou ◽  
Xiaojian Wu
Keyword(s):  
Tracking Control ◽  
High Speed ◽  
Unscented Kalman Filter ◽  
Linear Time ◽  
Autonomous Vehicle ◽  
Path Tracking ◽  
Steering Angle ◽  
Adhesion Coefficient ◽  
The Road ◽  
Vehicle Path

Considering that when a vehicle travels on a low friction coefficient road with high speed, the path tracking ability declines. To keep the performance of path tracking and improve the stabilization under that situation, this article presents approaches to estimate the parameters and control the vehicle. First, the key states of the vehicle and the road adhesion coefficient are estimated by the unscented Kalman filter. This is followed by applying the linear time-varying model-based predictive controller to achieve path tracking control, and the initial tire steering angle control rate is obtained. Finally, the steering angle compensation controller is simultaneously designed by a simple receding horizon corrector algorithm to improve vehicle stability when the path is tracked on a low-adhesion coefficient or at high speed. The performance of the proposed approach is evaluated by software CarSim and MATLAB/Simulink. Simulation results show that an improvement in the performance of path tracking and stabilization can be achieved by the integrated controller under the variable road adhesion coefficient condition and high speed with 110 km/h.

scholarly journals Integration of Cloud Computing and Artificial Intelligence in Driverless Car Using High Performance Behavioural Cloning

2019 ◽  
Vol 7 (8) ◽  
pp. 13-18
Author(s):  
Prabhat Kumar ◽  
Vishal Shrivastava
Keyword(s):  
Cloud Computing ◽  
High Performance ◽  
Autonomous Vehicle ◽  
Data Interpretation ◽  
Vital Role ◽  
Training Data ◽  
Steering Angle ◽  
The Road ◽  
Simulated Environment ◽  
Behavioral Cloning

Research on autonomous vehicle system has risen in the past couple of years. It has posed challenges to the researchers to develop an understanding about the real time scenarios. Deep Learning has demonstrated its extraordinary computational potential by transcending its abilities into more complex areas, where pattern matching, image recognition and behavioral cloning plays a vital role. The system consists of Image Processing and analyzing of the training data into behavioral cloning of the vehicle in a simulated environment. A control algorithm responsible for consolidating the sub systems calculations of the correct steering angle is used to keep the vehicle within the lane markings of the road. The solution proposed requires a better data collection and data interpretation. Addition of cloud computing fastens the data calculation and hence improves the performance of the system.

scholarly journals Explore User Behaviour in Semi-autonomous Driving

2019 ◽  
Vol 1 (1) ◽  
pp. 3871-3880
Author(s):  
Yuan Shi ◽  
Jeyhoon Maskani ◽  
Giandomenico Caruso ◽  
Monica Bordegoni
Keyword(s):  
Autonomous Vehicle ◽  
Autonomous Driving ◽  
Lateral Position ◽  
Steering Wheel ◽  
Physiological Indicators ◽  
The Road ◽  
Road Map ◽  
Human Driver ◽  
And Performance ◽  
Physiological Sensors

AbstractThe control shifting between a human driver and a semi-autonomous vehicle is one of the most critical scenarios in the road-map of autonomous vehicle development. This paper proposes a methodology to study driver's behaviour in semi-autonomous driving with physiological-sensors-integrated driving simulators. A virtual scenario simulating take-over tasks has been implemented. The behavioural profile of the driver has been defined analysing key metrics collected by the simulator namely lateral position, steering wheel angle, throttle time, brake time, speed, and the take-over time. In addition, heart rate and skin conductance changes have been considered as physiological indicators to assess cognitive workload and reactivity. The methodology has been applied in an experimental study which results are crucial for taking insights on users’ behaviour. Results show that individual different driving styles and performance are able to be distinguished by calculating and elaborating the data collected by the system. This research provides potential directions for establishing a method to characterize a driver's behaviour in a semi-autonomous vehicle.

scholarly journals Pedestrian Detection Based on Two-Stream UDN

2020 ◽  
Author(s):  
Wentong Wang ◽  
Lichun Wang ◽  
Xufei Ge ◽  
Jinghua Li ◽  
Baocai Yin
Keyword(s):  
Autonomous Vehicle ◽  
Pedestrian Detection ◽  
Activation Function ◽  
Practical Applications ◽  
Deep Network ◽  
The Road ◽  
Slowing Down ◽  
Deep Networks ◽  
The Difference ◽  
Computational Resources

Pedestrian detection is the core of driver assistance system, which collects the road conditions through the radars or cameras on the vehicle, judges whether there is a pedestrian in front of the vehicle, supports decisions such as raising the alarm, automatically slowing down or emergency stopping to keep pedestrians safe, and improves the security when the vehicle is moving. Suffered from weather, lighting, clothing, large pose variations and occlusion, the current pedestrian detection still has a certain distance from the practical applications. In recent years, deep networks have shown excellent performance for image detection, recognition and classification. Some researchers employed deep network for pedestrian detection and achieve great progress, but deep networks need huge computational resources which make it difficult to put into practical applications. In real scenarios of autonomous vehicle, the computation ability is limited. Thus, the shallow networks such as UDN (Unified Deep Networks) is a better choice since it performs well on consuming less computation resources. Base on UDN, this paper proposes a new deep network model named as two-stream UDN, which augments another branch for solving traditional UDN’s indistinction of the difference between trees / telegraph poles and pedestrians. The new branch accepts the upper third part of the pedestrian image as input, and the partial image has less deformation, stable features and more distinguished characters from other objects. For the proposed two-stream UDN, multi-input features including HOG feature, Sobel feature, color feature and foreground regions extracted by GrabCut segmentation algorithms are fed. Compared with the original input of UDN, the multi-input features are more conducive for pedestrian detection since the fused HOG features and significant objects are more significant for pedestrian detection. Two-stream UDN is trained through two steps: First, the two sub-networks are trained until converge; then we fuse results of the two subnets as the final result and feed it back to the two subnets to fine tune network parameters synchronously. To improve the performance, Softplus is adopted as activation function to obtain faster training speed, and positive samples are mirrored and rotated with small angle to make positive and negative samples more balanced.

scholarly journals Object Detection, Distributed Cloud Computing and Parallelization Techniques for Autonomous Driving Systems

2021 ◽  
Author(s):  
Edgar Cortés Gallardo Medina ◽  
Victor Miguel Velazquez Espitia ◽  
Daniela Chípuli Silva ◽  
Sebastián Fernández Ruiz de las Cuevas ◽  
Marco Palacios Hirata ◽  
...  
Keyword(s):  
Path Planning ◽  
Object Detection ◽  
Smart Cities ◽  
Autonomous Vehicle ◽  
Autonomous Driving ◽  
The Road ◽  
Vehicle System ◽  
End To End ◽  
On The Road ◽  
Distributed Cloud

Autonomous driving systems are increasingly becoming a necessary trend towards building smart cities of the future. Numerous proposals have been presented in recent years to tackle particular aspects of the working pipeline towards creating a functional end-to-end system, such as object detection, tracking, path planning, sentiment or intent detection. Nevertheless, few efforts have been made to systematically compile all of these systems into a single proposal that effectively considers the real challenges these systems will have on the road, such as real-time computation, hardware capabilities, etc. This paper has reviewed various techniques towards proposing our own end-to-end autonomous vehicle system, considering the latest state on the art on computer vision, DSs, path planning, and parallelization.

ACOUSTIC PANEL CHICKEN FEATHER WASTE ENVIRONMENTALLY FRIENDLY

2020 ◽  
Author(s):  
Ansarullah ◽  
Ramli Rahim ◽  
Baharuddin Hamzah ◽  
Asniawaty Kusno ◽  
Muhammad Tayeb
Keyword(s):  
Animal Feed ◽  
Environmentally Friendly ◽  
Selling Price ◽  
Chicken Feather ◽  
Chicken Feathers ◽  
The Road ◽  
Feather Waste ◽  
Chicken Feather Waste ◽  
Almost All ◽  
The Impact

Chicken feathers are the result of waste from slaughterhouses and billions ofkilograms of waste produced by various kinds of poultry processing. This hal is a veryserious problem for the environment because it causes the impact of pollution. Hasmany utilization of chicken feather waste such as making komocen, accessories,upholstery materials, making brackets to the manufacture of animal feed but from theresults of this activity cannot reduce the production of chicken feathers that hiscontinuously increase every year. This is due to the fact that the selling price of chickenmeat has been reached by consumers with middle to upper economic levels. This caneasily be a chicken menu in almost all restaurants and restaurants to the food stalls onthe side of the road. An alternative way of utilizing chicken feathers is to makecomposite materials in the form of panels. Recent studies have shown that the pvacmaterial can be utilized as a mixing and adhesive material with mashed or groundfeathered composites to form a panel that can later be used as an acoustic material.The test results show that the absorption of chicken feathers and pvac glue into panelscan absorb sound well with an absorption coefficient of 0.59, light. This result is veryeconomical so it is worth to be recommended as an acoustic material. Apart from theresults of research methods carried out is one of the environmentally friendly activitiesin particular the handling of waste problems

scholarly journals Automatic Roadway Features Detection with Oriented Object Detection

2021 ◽  
Vol 11 (8) ◽  
pp. 3531
Author(s):  
Hesham M. Eraqi ◽  
Karim Soliman ◽  
Dalia Said ◽  
Omar R. Elezaby ◽  
Mohamed N. Moustafa ◽  
...  
Keyword(s):  
Object Detection ◽  
Safety Evaluation ◽  
Autonomous Driving ◽  
Detection Accuracy ◽  
The Road ◽  
Detection Model ◽  
Detection Approach ◽  
Roadway Safety ◽  
Safety Features ◽  
Oriented Object

Extensive research efforts have been devoted to identify and improve roadway features that impact safety. Maintaining roadway safety features relies on costly manual operations of regular road surveying and data analysis. This paper introduces an automatic roadway safety features detection approach, which harnesses the potential of artificial intelligence (AI) computer vision to make the process more efficient and less costly. Given a front-facing camera and a global positioning system (GPS) sensor, the proposed system automatically evaluates ten roadway safety features. The system is composed of an oriented (or rotated) object detection model, which solves an orientation encoding discontinuity problem to improve detection accuracy, and a rule-based roadway safety evaluation module. To train and validate the proposed model, a fully-annotated dataset for roadway safety features extraction was collected covering 473 km of roads. The proposed method baseline results are found encouraging when compared to the state-of-the-art models. Different oriented object detection strategies are presented and discussed, and the developed model resulted in improving the mean average precision (mAP) by 16.9% when compared with the literature. The roadway safety feature average prediction accuracy is 84.39% and ranges between 91.11% and 63.12%. The introduced model can pervasively enable/disable autonomous driving (AD) based on safety features of the road; and empower connected vehicles (CV) to send and receive estimated safety features, alerting drivers about black spots or relatively less-safe segments or roads.

scholarly journals Object Detection, Distributed Cloud Computing and Parallelization Techniques for Autonomous Driving Systems

2021 ◽  
Vol 11 (7) ◽  
pp. 2925
Author(s):  
Edgar Cortés Gallardo Medina ◽  
Victor Miguel Velazquez Espitia ◽  
Daniela Chípuli Silva ◽  
Sebastián Fernández Ruiz de las Cuevas ◽  
Marco Palacios Hirata ◽  
...  
Keyword(s):  
Neural Networks ◽  
Cloud Computing ◽  
Path Planning ◽  
Object Detection ◽  
Short Term Memory ◽  
Smart Cities ◽  
Autonomous Vehicle ◽  
Computational Time ◽  
End To End ◽  
On The Road

Autonomous vehicles are increasingly becoming a necessary trend towards building the smart cities of the future. Numerous proposals have been presented in recent years to tackle particular aspects of the working pipeline towards creating a functional end-to-end system, such as object detection, tracking, path planning, sentiment or intent detection, amongst others. Nevertheless, few efforts have been made to systematically compile all of these systems into a single proposal that also considers the real challenges these systems will have on the road, such as real-time computation, hardware capabilities, etc. This paper reviews the latest techniques towards creating our own end-to-end autonomous vehicle system, considering the state-of-the-art methods on object detection, and the possible incorporation of distributed systems and parallelization to deploy these methods. Our findings show that while techniques such as convolutional neural networks, recurrent neural networks, and long short-term memory can effectively handle the initial detection and path planning tasks, more efforts are required to implement cloud computing to reduce the computational time that these methods demand. Additionally, we have mapped different strategies to handle the parallelization task, both within and between the networks.

Study on Driver and Vehicle System With Lane-Tracking Control System Using Steering Torque Input

2001 ◽  
Author(s):  
Masao Nagai ◽  
Hidehisa Yoshida ◽  
Kiyotaka Shitamitsu ◽  
Hiroshi Mouri
Keyword(s):  
Tracking Control ◽  
High Speed ◽  
Driving Simulator ◽  
Tracking System ◽  
Torque Control ◽  
Steering Wheel ◽  
Control Input ◽  
Steering Angle ◽  
Lane Tracking ◽  
Steering Torque

Abstract Although the vast majority of lane-tracking control methods rely on the steering wheel angle as the control input, a few studies have treated methods using the steering torque as the input. When operating vehicles especially at high speed, drivers typically do not grip the steering wheel tightly to prevent the angle of the steering wheel from veering off course. This study proposes a new steering assist system for a driver not with the steering angle but the steering torque as the input and clarifies the characteristics and relative advantages of the two approaches. Then using a newly developed driving simulator, characteristics of human drivers and the lane-tracking system based on the steering torque control are investigated.

Sign in / Sign up

Export Citation Format

Share Document