Abstract
This chapter explores the world of autonomous vehicles. Starting from the beginning, it covers the history of the automobile dating back to 1769. It explains how the first production automobile came about in 1885. The chapter dives into the history of auto safety, ranging from seatbelts to full-on autonomous features. One of the main focuses is the creation and implementation of artificial intelligent (AI), neural networks, intelligent agents, and deep Learning Processes. Combining the hardware on the vehicle with the intelligence of AI creates what we know as autonomous vehicles today.
TopBackground
In 1769, Nicolas-Joseph Cugnot built the first “automobile”. Cugnot was a military engineer who had experimented with many different steam engines. The French army wanted a faster and more efficient way to transport its cannons, so Cugnot built the “fardier à vapeu”. The vehicle had three wheels, weighed over 2.5 tons, and was powered by a boiler mounted above the front wheel. The weight distribution was so off, if there was not enough weight on the back it would tip forward. Add that the fire for the boiler had to be lit every 15 minutes, with the weight and slowness, the project was scrapped (The Library of Congress, n.d.).
Even though the first true automobile is up for debate, generally, Karl Friedrich Benz is credited for creating the first true automobile. In 1885 Benz built the “Benz Patent-Motorwagen” which was the first production automobile to be powered by a gasoline engine (Daimler, n.d.). The automobile was revolutionary for its time with a set of innovations never seen before. The two-stroke engine produced 2/3 horsepower which drove three wheels crafted out of steel and wood. No one had manufactured steel to be used for wheels before. The wheels even had solid rubber surrounding them, which was the turn of the century innovation that inspired tires today.
The car that truly revolutionized the industry, utilized technology, and became the best-selling car in American history: The Ford Model T. The Model T was produced from 1908 to 1927 by the Ford Motor Company (History.com Editors, 2010). It is known for its practicality and reliability. It was the car for the “common” people of America. It was able to be produced so widely due to Henry’s revolutionary idea for an assembly line (PBS, n.d.). Ford found out that to produce a low-cost car, there were 4 principals that needed to be followed: interchangeable parts, continuous flow, division of labor, and reduce wasted effort. Following these, Ford was able to reduce the cost of his model T down to less than $300 from the original $850. The simple motorized belt that moved parts along for people to assemble truly started the automotive industry.
Ever since the invention of the car and the production line, technology has not ceased its endeavor to grow in the automotive industry. In fact, automakers are creating new and exciting technology to make driving easier and more importantly safer. Besides the assembly line, one of the best “primitive” technologies integrated into vehicles was the electric ignition in 1911. Cranking the car to start posed somewhat of a safety hazard. Once the engine would start, sometimes the car would jump forward, injuring whoever cranked the car (Jardine Motors Group, n.d.).
Key Terms in this Chapter
Global Positioning System (GPS): A system of satellites, computers, and receivers that is able to determine the latitude and longitude of a receiver on Earth by calculating the time difference for signals from different satellites to reach the receiver.
Autonomous Vehicles: Is a vehicle that is capable of sensing its surroundings and moves with little or no driver assist.
Artificial Intelligent (AI): A branch of computer science dealing with tasks that normally require human intelligence, such as visual perception, speech recognition, decision-making, and translation between languages.
Lisp: A computer programming language developed in late 1950s by John McCarthy at the Massachusetts Institute of Technology (MIT). It is based on a distinctive, fully parenthesized prefix notation.
Unsupervised Learning: Is the training of an artificial intelligence (AI) algorithm using a dataset that is neither classified nor labeled and allowing the algorithm to process the dataset and find patterns without guidance.
Neural Network: Is inspired by the biological neural networks that constitute animal brains. It consists of a series of algorithms that discover underlying patterns in a dataset through a process that mimics the way the human brain operates.
Supervised Learning: Happens when a set of predefined images or numbers have labels on them. It maps an input to an output based on example input-output pairs.
Perception Action Cycle: Is an intuitive explanation of the technical setting of reinforcement learning. It is the circular flow of information that takes place between a moving object and its environment in form of a sensory-guided sequence of behavior.
Reinforced Learning: Is about taking suitable action to maximize reward in a particular situation. Reinforcement learning differs from the supervised learning in a way that in supervised learning there is training data whereas in reinforcement learning, there is no training dataset. Without training dataset, reinforcement learning has to learn from its experience.