Self Driving

PLS-SEM technology, awareness of driving support systems, and perceived usefulness of new technologies had a weak but significant direct impact. The results of study will provide essential information for the successful integration of self-driving technologies into the innovation systems of less-developed countries.

This paper deals with a 2D unity simulation of an autonomous car learning to drive in a simplified environment containing only lane and static obstacles. Learning is performed using the neural network and evolutionary algorithm. The cars navigate by evolving themselves from the previous generation. The neural network used in this paper is standard, fully connected, feed forward neural network. The cars are steered by a feed forward Neural Network. The weights of the network are trained using a modified genetic algorithm.

The advancement of artificial intelligence (AI) has truly stimulated the development and deployment of autonomous vehicles (AVs) in the transportation industry. Fueled by big data from various sensing devices and advanced computing resources, AI has become an essential component of AVs for perceiving the surrounding environment and making appropriate decision in motion. To achieve goal of full automation (i.e., self-driving), it is important to know how AI works in AV systems. Existing research have made great efforts in investigating different aspects of applying AI in AV development. However, few studies have offered the research community a thorough examination of current practices in implementing AI in AVs. Thus, this paper aims to shorten the gap by providing a comprehensive survey of key studies in this research avenue. Specifically, it intends to analyze their use of AIs in supporting the primary applications in AVs: 1) perception; 2) localization and mapping; and 3) decision making. It investigates the current practices to understand how AI can be used and what are the challenges and issues associated with their implementation. Based on the exploration of current practices and technology advances, this paper further provides insights into potential opportunities regarding the use of AI in conjunction with other emerging technologies: 1) high definition maps, big data, and high performance computing; 2) augmented reality (AR)/virtual reality (VR) enhanced simulation platform; and 3) 5G communication for connected AVs. This paper is expected to offer a quick reference for researchers interested in understanding the use of AI in AV research.

The IGVC offers a design experience that is at the very cutting edge of engineering education, with a particular focus in developing engineering control/sensor integration experience for the college student participants. A main challenge area for teams is the proper processing of all the vehicle sensor feeds, optimal integration of the sensor feeds into a world map and the vehicle leveraging that world map to plot a safe course using robust control algorithms. This has been an ongoing challenge throughout the 26 year history of the competition and is a challenge shared with the growing autonomous vehicle industry. High consistency, reliability and redundancy of sensor feeds, accurate sensor fusion and fault-tolerant vehicle controls are critical, as even small misinterpretations can cause catastrophic results, as evidenced by the recent serious vehicle crashes experienced by self-driving companies including Tesla and Uber Optimal control techniques & sensor selection/integration int...

Synopsis: The paper presents a survey of surveyed experts’ assumptions of how three different emerging automated mobility technical-organizational solutions: Autonomous Automobiles, Self-Driving Car-Sharing and Ride-Hailing, and Driverless Shuttles relate to the metropolitan structures of both cities and suburban areas.

In this research, we propose the use of end-to-end deep learning simulation approach for assisting the design of LiDAR. The results show that two million points per second rate is optimal for point cloud based intersection classification task. The detection range of up to 100 meters corresponds to optimal classification performance. The 10 degree of upper field of view and 10 degree of lower field of view is sufficient for intersection classification. A linear increase of classification accuracy from 10 to 70 channels is evident. The research bridges the gap of lower level LiDAR simulation and development and self-driving visual tasks and expected to find applications to improve self-driving performance and safety.

The dramatic surge in the development of autonomous vehicles has generated a need for, among others, improving detection and ranging accuracy. Various technologies and techniques have been proposed and adopted for autonomous vehicles, such as computer vision, in conjunction with machine learning and deep learning-neural network. Despite many attempts to improve the accuracy of detection and ranging, the computational load in training the neural network due to the requirement of massive amount of data had increased to a significant extent, along with the cost of operation. Light Detection and Ranging (LiDAR) systems are a new approach to improve the detection and ranging accuracy. However, LED Detection and Ranging (LEDDAR) based systems have not been explored so far. Herein, we present an analysis of the method of detection and ranging using LED and determine its performance for different number of users using Unipolar Optical Code Division Multiple Access (OCDMA) Codes. This was done using probability of error vs. Signal-to-Noise Ratio (SNR) and Distance (in m) using misdetection and false alarm analysis for a given transmitted power of LED obeying the current standards. The method of LED based beamforming by deploying multiple LED's in an array is proposed to improve the detection and ranging accuracy. Finally, the results show that OCDMA based OOC codes show a low probability of error for a given SNR and Distance and outperformed other OCDMA techniques such as prime codes and hence indicate that OOC codes will be an optimal choice that can be coded in LED's for the use in self driving cars.

This "ILLUSTRATED TECHNICAL PAPER" presents the slides describing the contents of the short-course "Intelligent Communication Resource Allocation for Smart City with Machine Learning and SDN OpenFlow". ABSTRACT Smart city projects address many of the current problems afflicting high populated areas and cities and, as such, are a target for government, institutions and private organizations that plan to explore its foreseen advantages. In this scenario, this course presents and analyses the impact and perspectives on adopting software-defined networking and machine learning as innovative approaches for smart city project development and deployment. A framework layered view of smart city projects is proposed with a discussion about software-defined networking and machine learning impacts on innovation. This is followed by a case of use that demonstrates the potential benefits of cognitive learning for smart cities using Case-based Reasoning (CBR) for intelligent communications resource (bandwidth) allocation. The target is a MPLS network using BAM models as the broker for bandwidth allocation for Smart City application and systems. It is argued that the complexity of smart city projects do require new innovative approaches that potentially result in more efficient and smarter systems.

Modern thinking regarding transportation seems to overlook the unavoidable fact that both "operator error" and "Artificial Intelligence error" will forever cause hundreds of thousands of automotive accidents and deaths if and when "driverless vehicles" would some day be refined.  Still, such "self-driving" vehicles would never "safely" be able to go faster than around 50 mph.  Some "experts" now concede that it would be many decades before this situation might even become possible.

Instead, a far safer and far better technology ALREADY exists.  For the past sixty years, many hundreds of billions of perfectly safe "Drive-Through Banking" transactions have proceeded where "canisters" whiz around inside pneumatic tubes that carry money and papers between Bank Tellers and vehicle drivers.

Larger-scale structures of such pneumatic tubes also already exist where large-diameter reinforced concrete culverts carry water and air underneath highways. 
also, fifty years ago, the 700-mile-long Alyeska Oil Pipeline was built across Alaska to carry liquid crude petroleum to ocean freighters.  That Alyeska Oil Pipeline uses aircraft jet engines to power the flow of the oil.

A variation of that Alyeska metal tube provides the answer we want.  (See the culvert installation photo below).  Five-foot-diameter, very straight, reinforced concrete culverts can be installed on, above (on pillars) or below (buried underground) on highway medians, where aircraft jet-engine exhaust at 230 mph could drive SUV-sized "canisters" or "Pods" (which contain passengers or freight) which would actually physically "fly" inside those concrete culverts at exactly 200.0 mph, by a process called Bernoulli Lift.

News stories regularly tell us about electric vehicles having their thousands of batteries explode and of driverless vehicles killing pedestrians and bicyclists.  They rarely mention that such vehicles rarely go faster than 50 mph or for more than a few hours. 

This very different technology absolutely ensures that NO DANGER EXISTS for anyone, as all the Pods are all forever safely inside very sturdy reinforced concrete culverts.  Better still, all of the passengers and freight always travels at precisely the same speed, 200.0 mph, so even inside the culverts, no collisions of any sort are possible.


No pollution. Commute 20 miles in 9 minutes for $0.25 with no traffic.

No Fossil Fuels. Absolutely safe driverless vehicles, using just solar or wind power.

TRANS Super-Efficient Transportation and Freight System replaces cars, trucks, trains, buses, and airliners.

The development in vehicle short-range communication, sensing, and in-vehicle computing technology provides an opportunity for wide-scale deployment of self-driving vehicles (SDVs). The issue of intersection control for these future vehicles is one of the emerging research issues. This research focuses on the question of traffic control framework for SDVs, while also attempting to incorporate the advantages and disadvantages to users ensuing from a control framework (i.e., delay distribution). The framework developed from these considerations is a version of Priority System (PS). In addition, distributed vehicle intelligence has been used to formulate a self-organizing control solution for trajectory adjustment. Considering that PS depends on end user responsibility, research presented here evaluates the proposed control framework by including human decision-making. First, this paper focuses on development of web-based experimentation for allowing user interaction with PS. In addition, this paper will use the information collected from the web-based experiment to develop simulation scenarios for an isolated intersection. Proposed control framework has been compared with the conventional actuated traffic signal control. The conclusion from the evaluation is that PS could affect the distribution of delay among the users, until the oversaturation threshold is reached. Finally, the paper presents a summary of results, conclusions, and recommendations for further research. The research presented here raises several implications for further considerations regarding intersection control principles for SDV technology.

Digitalization, as a recent mega-trend, seeks to ease life with notable new solutions, one being autonomous, self-driving technology for vehicles. The radical innovation involved in a global spread and acceptance of self-driving vehicles will drastically change people's lives and also the structure of cities and aspects of urban mobility. The first phase in developing such vehicles has been reached: technology is being fine-tuned in the live street environment of 76 cities. However, the prospect divides world society, mainly through serious, unanswered social, ethical, environmental and economic issues it raises. The study explores the controversial challenges in what promises to transform significantly the daily life of our civilization. The issue of selfdriving is integrated into the framework of responsible innovation, so offering possible ways in which innovation management can address the identified challenges.