scholarly journals Imitating a Safe Human Driver Behaviour in Roundabouts Through Deep Learning

2020 ◽  
Vol 19 (1) ◽  
pp. 85-88
Author(s):  
A. S. J. Cervera ◽  
F. J. Alonso ◽  
F. S. García ◽  
A. D. Alvarez
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Autonomous Vehicles ◽  
Autonomous Vehicle ◽  
Driver Behaviour ◽  
Safety Issues ◽  
Current State ◽  
Surrounding Environment ◽  
Human Driver ◽  
State Of The Environment

Roundabouts provide safe and fast circulation as well as many environmental advantages, but drivers adopting unsafe behaviours while circulating through them may cause safety issues, provoking accidents. In this paper we propose a way of training an autonomous vehicle in order to behave in a human and safe way when entering a roundabout. By placing a number of cameras in our vehicle and processing their video feeds through a series of algorithms, including Machine Learning, we can build a representation of the state of the surrounding environment. Then, we use another set of Deep Learning algorithms to analyze the data and determine the safest way of circulating through a roundabout given the current state of the environment, including nearby vehicles with their estimated positions, speeds and accelerations. By watching multiple attempts of a human entering a roundabout with both safe and unsafe behaviours, our second set of algorithms can learn to mimic the human’s good attempts and act in the same way as him, which is key to a safe implementation of autonomous vehicles. This work details the series of steps that we took, from building the representation of our environment to acting according to it in order to attain safe entry into single lane roundabouts.

scholarly journals Behavior Identification and Prediction for a Probabilistic Risk Framework

2019 ◽  
Author(s):  
Jasprit S. Gill ◽  
Pierluigi Pisu ◽  
Venkat N. Krovi ◽  
Matthias J. Schmid
Keyword(s):  
Autonomous Vehicles ◽  
Adaptive Estimation ◽  
Autonomous Vehicle ◽  
Search Space ◽  
Complex Environments ◽  
Current State ◽  
Risk Framework ◽  
Detailed Simulation ◽  
The Right ◽  
State Of The Environment

Abstract Operation in a real world traffic requires the ability to plan motion in complex environments (multiple moving participants) from autonomous vehicles. Navigation through such environments necessitates the provision of the right search space for the trajectory or maneuver planners so that the safest motion for the ego vehicle can be identified. Analyzing risks based on the predicted trajectories of all traffic participants (given the current state of the environment and its participants) aids in the proper formulation of this search space. This study introduces a fresh taxonomy of safety and risk that an autonomous vehicle should be capable of handling. It formulates a reference system architecture for implementation as well as describes a novel way of identifying and predicting the behaviors of other traffic participants utilizing classic Multi Model Adaptive Estimation (MMAE). Detailed simulation results and a discussion about the associated tuning of the implemented model conclude this work.

scholarly journals Computer vision based obstacle detection and target tracking for autonomous vehicles

2021 ◽  
Vol 336 ◽  
pp. 07004
Author(s):  
Ruoyu Fang ◽  
Cheng Cai
Keyword(s):  
Neural Network ◽  
Computer Vision ◽  
Deep Learning ◽  
Target Tracking ◽  
Real Time ◽  
Autonomous Vehicles ◽  
Autonomous Vehicle ◽  
Obstacle Detection ◽  
Pid Algorithm ◽  
Deep Learning Neural Network

Obstacle detection and target tracking are two major issues for intelligent autonomous vehicles. This paper proposes a new scheme to achieve target tracking and real-time obstacle detection of obstacles based on computer vision. ResNet-18 deep learning neural network is utilized for obstacle detection and Yolo-v3 deep learning neural network is employed for real-time target tracking. These two trained models can be deployed on an autonomous vehicle equipped with an NVIDIA Jetson Nano motherboard. The autonomous vehicle moves to avoid obstacles and follow tracked targets by camera. Adjusting the steering and movement of the autonomous vehicle according to the PID algorithm during the movement, therefore, will help the proposed vehicle achieve stable and precise tracking.

Detection and defense of cyberattacks on the machine learning control of robotic systems

2021 ◽  
pp. 154851292110438
Author(s):  
George W Clark ◽  
Todd R Andel ◽  
J Todd McDonald ◽  
Tom Johnsten ◽  
Tom Thomas
Keyword(s):  
Machine Learning ◽  
Autonomous Vehicles ◽  
Defense Mechanisms ◽  
Autonomous Vehicle ◽  
Learning Algorithms ◽  
Learning Model ◽  
Machine Learning Algorithms ◽  
Robotic Systems ◽  
Machine Learning Model ◽  
Attack Surface

Robotic systems are no longer simply built and designed to perform sequential repetitive tasks primarily in a static manufacturing environment. Systems such as autonomous vehicles make use of intricate machine learning algorithms to adapt their behavior to dynamic conditions in their operating environment. These machine learning algorithms provide an additional attack surface for an adversary to exploit in order to perform a cyberattack. Since an attack on robotic systems such as autonomous vehicles have the potential to cause great damage and harm to humans, it is essential that detection and defenses of these attacks be explored. This paper discusses the plausibility of direct and indirect cyberattacks on a machine learning model through the use of a virtual autonomous vehicle operating in a simulation environment using a machine learning model for control. Using this vehicle, this paper proposes various methods of detection of cyberattacks on its machine learning model and discusses possible defense mechanisms to prevent such attacks.

Comprehensive Overview of Neural Networks and Its Applications in Autonomous Vehicles

2019 ◽  
pp. 159-173
Author(s):  
Jay Rodge ◽  
Swati Jaiswal
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Neural Networks ◽  
Deep Learning ◽  
Autonomous Vehicles ◽  
Autonomous Vehicle ◽  
Learning Algorithms ◽  
Activation Functions ◽  
Comprehensive Overview ◽  
Unit Component

Deep learning and Artificial intelligence (AI) have been trending these days due to the capability and state-of-the-art results that they provide. They have replaced some highly skilled professionals with neural network-powered AI, also known as deep learning algorithms. Deep learning majorly works on neural networks. This chapter discusses about the working of a neuron, which is a unit component of neural network. There are numerous techniques that can be incorporated while designing a neural network, such as activation functions, training, etc. to improve its features, which will be explained in detail. It has some challenges such as overfitting, which are difficult to neglect but can be overcome using proper techniques and steps that have been discussed. The chapter will help the academician, researchers, and practitioners to further investigate the associated area of deep learning and its applications in the autonomous vehicle industry.

scholarly journals An Initial Investigation of the Effects of a Fully Automated Vehicle Fleet on Geometric Design

2019 ◽  
Vol 2019 ◽  
pp. 1-10 ◽  
Author(s):  
John Khoury ◽  
Kamar Amine ◽  
Rima Abi Saad
Keyword(s):  
Autonomous Vehicles ◽  
Autonomous Vehicle ◽  
Real Life ◽  
Geometric Design ◽  
Design Elements ◽  
Sight Distance ◽  
Human Driver ◽  
Projected Change ◽  
Vehicle Fleet ◽  
Stopping Sight Distance

This paper investigates the potential changes in the geometric design elements in response to a fully autonomous vehicle fleet. When autonomous vehicles completely replace conventional vehicles, the human driver will no longer be a concern. Currently, and for safety reasons, the human driver plays an inherent role in designing highway elements, which depend on the driver’s perception-reaction time, driver’s eye height, and other driver related parameters. This study focuses on the geometric design elements that will directly be affected by the replacement of the human driver with fully autonomous vehicles. Stopping sight distance, decision sight distance, and length of sag and crest vertical curves are geometric design elements directly affected by the projected change. Revised values for these design elements are presented and their effects are quantified using a real-life scenario. An existing roadway designed using current AASHTO standards has been redesigned with the revised values. Compared with the existing design, the proposed design shows significant economic and environmental improvements, given the elimination of the human driver.

scholarly journals An Overview of Lidar Imaging Systems for Autonomous Vehicles

2019 ◽  
Vol 9 (19) ◽  
pp. 4093 ◽  
Author(s):  
Santiago Royo ◽  
Maria Ballesta-Garcia
Keyword(s):  
Autonomous Vehicles ◽  
State Of The Art ◽  
Autonomous Vehicle ◽  
Single Point ◽  
Imaging Systems ◽  
Light Sources ◽  
Final Solution ◽  
Large Uncertainty ◽  
Current State ◽  
The Subject

Lidar imaging systems are one of the hottest topics in the optronics industry. The need to sense the surroundings of every autonomous vehicle has pushed forward a race dedicated to deciding the final solution to be implemented. However, the diversity of state-of-the-art approaches to the solution brings a large uncertainty on the decision of the dominant final solution. Furthermore, the performance data of each approach often arise from different manufacturers and developers, which usually have some interest in the dispute. Within this paper, we intend to overcome the situation by providing an introductory, neutral overview of the technology linked to lidar imaging systems for autonomous vehicles, and its current state of development. We start with the main single-point measurement principles utilized, which then are combined with different imaging strategies, also described in the paper. An overview of the features of the light sources and photodetectors specific to lidar imaging systems most frequently used in practice is also presented. Finally, a brief section on pending issues for lidar development in autonomous vehicles has been included, in order to present some of the problems which still need to be solved before implementation may be considered as final. The reader is provided with a detailed bibliography containing both relevant books and state-of-the-art papers for further progress in the subject.

scholarly journals The Convolution Addressing the Conundrum of Liability and Privacy in the Age of Autonomous Vehicles

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Aarushi Kapoor ◽  
Khushi Sharma
Keyword(s):  
Growth Rate ◽  
Future Development ◽  
Automotive Industry ◽  
Privacy Protection ◽  
Autonomous Vehicles ◽  
Autonomous Vehicle ◽  
Human Driver ◽  
The Future ◽  
New Framework

The Automotive Industry has registered an impeccable growth rate since the adoption of autonomous vehicles by vehicle manufacturers in their high-end models. These fully autonomous vehicles are poised to replace the traditional human driver. Hence, the whole set of laws defining liability in the event of an accident involving a vehicle have to be reformed. An autonomous vehicle being sued in lieu of a human driver, would be impractical. With the accidents involving autonomous vehicles increasing, newly minted laws like that of Michigan Harbor Lacunas are forming to address the question of liability and as a consequence of which the innocent (the manufacturer in so many cases) is held absolutely liable, despite his pleading defense. Such a harsh stance is unhealthy for the development of technology. Apart from the conundrum surrounding liability there are other dimensions which are equally unaddressed when it comes to automation. These autonomous vehicles rely on data, thereby adding to the vulnerability of protection of an individual’s privacy. These brimming chaos are likely to hamper the aggrandizement of technology and subsequent protection of commercial interests.This Article is an attempt to comprehensively analyze the uncertainty surrounding the questions of liability and privacy protection for autonomous vehicles. It takes into account the technology friendly interpretation of law, which will balance the diametrically opposite variables. It draws the laws from the existing set of principles available. Further, it proposes a new framework eliminate obscurity and concludes on a positive note with recommendations which are likely to accentuate the effectiveness of the current laws and lay down a steppingstone for the future development of laws.

scholarly journals Accuracy–Power Controllable LiDAR Sensor System with 3D Object Recognition for Autonomous Vehicle

Sensors ◽  
2020 ◽  
Vol 20 (19) ◽  
pp. 5706
Author(s):  
Sanghoon Lee ◽  
Dongkyu Lee ◽  
Pyung Choi ◽  
Daejin Park
Keyword(s):  
Power Consumption ◽  
Autonomous Vehicles ◽  
Control Algorithm ◽  
Autonomous Vehicle ◽  
Sleep Mode ◽  
Cmos Process ◽  
Battery Power ◽  
Surrounding Environment ◽  
Transmission Period ◽  
Static Power

Light detection and ranging (LiDAR) sensors help autonomous vehicles detect the surrounding environment and the exact distance to an object’s position. Conventional LiDAR sensors require a certain amount of power consumption because they detect objects by transmitting lasers at a regular interval according to a horizontal angular resolution (HAR). However, because the LiDAR sensors, which continuously consume power inefficiently, have a fatal effect on autonomous and electric vehicles using battery power, power consumption efficiency needs to be improved. In this paper, we propose algorithms to improve the inefficient power consumption of conventional LiDAR sensors, and efficiently reduce power consumption in two ways: (a) controlling the HAR to vary the laser transmission period (TP) of a laser diode (LD) depending on the vehicle’s speed and (b) reducing the static power consumption using a sleep mode, depending on the surrounding environment. The proposed LiDAR sensor with the HAR control algorithm reduces the power consumption of the LD by 6.92% to 32.43% depending on the vehicle’s speed, compared to the maximum number of laser transmissions (Nx.max). The sleep mode with a surrounding environment-sensing algorithm reduces the power consumption by 61.09%. The algorithm of the proposed LiDAR sensor was tested on a commercial processor chip, and the integrated processor was designed as an IC using the Global Foundries 55 nm CMOS process.

An End-to-End Fully Automatic Bay Parking Approach for Autonomous Vehicles

2018 ◽  
Author(s):  
Rui Li ◽  
Weitian Wang ◽  
Yi Chen ◽  
Srivatsan Srinivasan ◽  
Venkat N. Krovi
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Autonomous Vehicles ◽  
Autonomous Vehicle ◽  
Human Vision ◽  
Automated Driving ◽  
Learning Framework ◽  
Research Platform ◽  
Automatic Parking ◽  
Fully Automatic

Fully automatic parking (FAP) is a key step towards the age of autonomous vehicle. Motivated by the contribution of human vision to human parking, in this paper, we propose a computer vision based FAP method for the autonomous vehicles. Based on the input images from a rear camera on the vehicle, a convolutional neural network (CNN) is trained to automatically output the steering and velocity commands for the vehicle controlling. The CNN is trained by Caffe deep learning framework. A 1/10th autonomous vehicle research platform (1/10-SAVRP), which configured with a vehicle controller unit, an automated driving processor, and a rear camera, is used for demonstrating the parking maneuver. The experimental results suggested that the proposed approach enabled the vehicle to gain the ability of parking independently without human input in different driving settings.

scholarly journals CRISPRpred(SEQ): a sequence based tool for sgRNA on target activity prediction [(almost) beating Deep Learning pipelines by traditional machine learning]

2019 ◽  
Author(s):  
Ali Haisam Muhammad Rafid ◽  
Md. Toufikuzzaman ◽  
Mohammad Saifur Rahman ◽  
M. Sohel Rahman
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Genome Editing ◽  
Cell Lines ◽  
Genetic Diseases ◽  
Machine Learning Techniques ◽  
Activity Prediction ◽  
Current State ◽  
Learning Techniques ◽  
Target Activity

AbstractAn accurate and fast genome editing tool can be used to treat genetic diseases, modify crops genetically etc. However, a tool that has low accuracy can be risky to use, as incorrect genome editing may have severe consequences. Although many tools have been developed in the past, there are still room for further improvement. In this paper, we present CRISPRpred(SEQ), a sequence based tool for sgRNA on target activity prediction that leverages only traditional machine learning techniques. We compare the results of CRISPRpred(SEQ) with that of DeepCRISPR, the current state-of-the-art, which uses a deep learning pipeline. In spite of using only traditional machine learning methods, we are able to beat DeepCRISPR for the three out of four cell lines in the benchmark dataset convincingly (2.174%, 6.905% and 8.119% improvement for the three cell lines), which is quite outstanding.

Sign in / Sign up

Export Citation Format

Share Document