A study into the design of track based autonomous vehicles with implementation of high level systems for optimal speed and safety
What is AI?
The official idea and definition behind AI was coined by John McCarthy in 1955 at the Dartmouth Conference. McCarthy proposed, ‘Every aspect of learning or any other feature of intelligence can in principle be so precisely described that a machine can be made to simulate it. An attempt will be made to find how to make machines use language, form abstractions and concepts, solve kinds of problems now reserved for humans, and improve themselves.’ AI is a machine with the ability to solve problems that are usually done by humans with our intelligence. A computer would demonstrate a form of intelligence, when it learns how to improve itself at solving the problems we have programmed them to do.
The proposal done at the Dartmouth Conference in 1955 highlights 7 areas of artificial intelligence, today there is a lot more but this is the originals: Simulating higher functions of the human brain, programming a computer to use general language, arranging hypothetical neurons in a manner so that they can form concepts, a way to determine and measure problem complexity, self-improvement, abstraction: defined as the quality of dealing with ideas rather than events, randomness and creativity. Over the past 60 years, realistically we have managed to complete most of them to a certain extent, however some areas on only just starting to be explored.
According to Jack Copeland, who has wrote several books on AI, thinks the most important facts on artificial intelligence are:
• Generalization Learning, which is learning which enables the learner to be able to perform better in situation which they have not previously encountered
• Reasoning, to reason is to draw conclusions appropriate to the situation in hand
• Problem Solving, using the data given, find ‘x’
• Perception, analysing features and relationships between objects, sensory systems in self-driving cars are an example
• Language Understanding, understanding language by following syntax and other rules, just like a human would
Some examples of artificial intelligence include: Machine learning, Computer vision, Natural language processing, Robotics, Pattern recognition and Knowledge management. There are also different types of AI in terms of approach. For example there is strong AI and weak AI. Strong AI is stimulating the human brain by building systems that think and in the process, give us an insight on how the brain works, we are nowhere near this stage yet. Strong AI can do anything as well/better than a human. Weak AI is a system that behaves like a human but doesn't give us an insight on how the brain works. Weak AI achieves only the result of a human.
Googles ‘deep learning’ mimics the structure of the human brain by using neural networks. The system uses nodes that act as artificial neurons connecting information. Neural networks are a subset of machine learning, machine learning refers to algorithms that enables software to improve its performance overtime as it obtains more data. This is programming by input and output examples, instead of just coding.
(ColdFusion, 19th July 2016)
The Fourth Industrial Revolution
Industry 4.0 is the vision of tomorrows manufacturing. Products will be able to find their way independently through the production process. In intelligent factories, machines and products communicate with each other. The objective is highly flexible, individualised and resource friendly mass production.
The first industrial revolution, at the end of the 18th century, was when the first steam engines and the intelligent use of hydro power revolutionised production. The second industrial revolution, in the late 19th century, saw the rise in electrical engineering and mass production. The first conveyer belt was used in 1870, in slaughter houses. The third industrial revolution, in the mid-1970s, was when electronics and IT began to expand rapidly into industry. Production became increasing based on computerised controlling systems. The forth industrial revolution is still a vision, but experts believe it will become a reality in the next 20 years. In ‘smart factories’ everything will be interconnected wirelessly.
What are Autonomous Vehicles?
Autonomous Vehicles are vehicles that use sensors, lasers and cameras to navigate the roads. The sensory information is then processed to navigate appropriate pathways for the vehicle to take, avoiding any obstacles and also obeying the road signs. The car uses a digital map, which can be constantly updated according to sensory input. This allows the vehicle to adapt to changing situations, as well as travel through previously unknown territories. There are 5 different levels of automation that an autonomous vehicles can reach, Level 0: The driver has complete control of vehicle at all times. Level 1: Some vehicle controls are automated such as automatic braking. Level 2: Two or more controls can be automated at the same time such as cruise control and lane keeping. Level 3: These cars can handle ‘dynamic driving tasks’ but still need someone to be there, supervising. Level 4: Driver not expected to play any part in the driving process at all in certain environments. Level 5: These car can operate without any driver present.
(FIA, 24th April 2017)
Examples of companies that are researching autonomous vehicles