2. TABLE OF CONTENT
Introduction
Microscopic Traffic Models using ARTIFICIAL INTELLIGENCE
(A.I)
Uses of Artificial Intelligence traffic models
Advantages and Disadvantages
Review
Conclusion
3. Introduction
Road traffic models : It provide the representation of the highway
network in terms of the capacity it's provide and the volume of traffic
using it.
Traffic Modelling: is essentially a computer model a mathematical
model used to predict people trips pattern and travel choice so that
we can understand uses of Road and public transport on the network.
They are different types of traffic flow models and they can be
classified in various ways for example they can be classified to the
level details. There are microscopic, macroscopic and mesoscopic
traffic models
4. Introduction cont…
Microscopic traffic models: it's formulate the interactions between
individual vehicle, and the i.e details of traffic flow and the
interaction taking place within it. It stimulate single vehicle driver
unit. The dynamic variables of the models represent microscopic
property like the position and velocity of single-vehicle (popping
2013).
Microscopic models of traffic flow seek to analyse the flow of traffic
by modelling driver-driver and driver-road interaction within a traffic
stream which respectively analyses the interaction between a driver
and another driver on road and a single driver on the different
features of a road. Microscopic stimulation, models the passengers
and a vehicle as individual entities rather than as a flow of
movement.
5. Introduction cont…
Mesoscopic traffic models: were developed to fill the gap between the family of
microscopic models that describe the behaviour of individual vehicles and the
family of macroscopic model that describe traffic as a Continuum flow. Traditional
mesoscopic model describe vehicle flow in aggregate terms such as in probability
distribution however behavioral rules are define for individual vehicle. The family
includes headway distribution models, cluster models, gas-kinetic models and
macroscopic models derived from them.
Macroscopic traffic models: it consider the traffic flow, i.e macroscopic models
are used to analyse traffic flow as a whole contrary to microscopic models which
analysed the behaviour of every individual car. It consider the aggregate behaviour
of traffic flow while microscopic models consider the interaction of individual
vehicle. Macroscopic traffic models is a mathematical traffic model that formulate
the relationship among traffic flow characteristic like density, flow and mean
speed of a traffic stream etc... such model are conventionally arrived at by
integrating microscopic traffic flow model and converting the single - entity level
characteristics to comparable system level characteristics an example is the two-
floor model.
6. Introduction cont…
Artificial intelligence: is the simulation of human intelligence
processes by machines, especially computer systems. Specific
applications of AI include expert systems, natural language
processing, speech recognition and machine vision.
Types of artificial intelligence
Arend Hintze, 2016
Reactive machines
Limited memory
Theory of mind
Self-awareness
7. Microscopic Traffic Model Using AI
Artificial intelligent traffic model: generate a fleet of semi intelligent
with which a human driver interacts with in a virtual driving simulation
environment.
AI is really going to be driving the future of transportation not only
the vehicle driving experience aspect but all sorts of aspect of
transportation artificial intelligence is taking centre stage.
AI is transforming how we drive cars and how cars will soon drive us
to, deep learning - a form of AI- is now able to drive superhuman level
of perception and understanding from natural language processing to
360 degree situational awareness (Sky Matthews 2016.).
Fuzzy models is a method of reasoning that resemble human
reasoning this approach is similar to how humans perform decision
making and it's involved all intermediate possibilities between YES and
NO (Sayantini, 2019.). Fuzzy logic in AI provides valuable flexibility for
reasoning.
8. Uses of AI in Traffic Modelling
Urban Planning
Traffic Lights – Traffic signal control system
Smart Parking
Law Enforcement in Traffic using AI
Traffic flowing AI [Flowing traffic – With the power of AI]
Quality Data – The Key to artificial intelligence in road
traffic
9. Importance of AI in Traffic Modelling
Cyber security issues
The Smart City – AI Traffic Systems in cities, Traffic
Management in a Smart City
Adaptive traffic control system (ATCS)
Automated vehicles
Delivery Drone
Intelligent parking planning
Reducing Traffic Congestions – Improving Road Traffic
Flow
Safety and Emergency Situations
Transit Planning – Intelligent Transportation Systems
11. Advantages of AI in Traffic Modelling
Good at detail-oriented jobs;
Reduced time for data-heavy tasks;
Delivers consistent results; and
AI-powered virtual agents are always available.
12. Disadvantages of AI in Traffic Modelling
Expensive;
Requires deep technical expertise;
Limited supply of qualified workers to build AI tools;
Only knows what it's been shown; and
Lack of ability to generalize from one task to another.
13. Conclusion
In addition to AI's fundamental role in Traffic Modelling,
operating autonomous vehicles, AI technologies are used in
transportation to manage traffic, predict flight delays, and
make ocean shipping safer and more efficient.