Optimal Road Trip Planning using Genetic Algorithm
₹6,000.00 Exc Tax
Analyzing optimal road trip planning using Genetic Algorithm with Google maps
Platform : Python
Delivery Duration : 3-4 working Days
100 in stock
The accurate and reliable Trip-generation Forecasting Model is the most basic and important part of the traffic forecasting model. This project focuses on genetic algorithm which has an excellent Global search capability with trip-generation forecasting model in order to achieve the purpose of improving the accuracy of prediction. One of the difficulty in planning a road trip is deciding where to stop along the way. The U.S. is large and diverse, it’s especially hard to make a road trip that will appeal to everyone.
The proposed system should satisfy the path constraints which should meet the drivers’ preferences as well as the alternative path constraints and limit the joint failure probability for candidate paths.
The characteristics of the proposed algorithm are the following:
1) The trip must make at least one stop in all 48 states in the contiguous U.S.
2) The trip would only make stops at National Natural Landmarks, National Historic Sites, National Parks, or National Monuments.
The algorithm is tested on randomly generated road routes and the numerical results show the efficiency of the approach
With the list of landmarks , we have to find the “true” distance between all the landmarks. Since we cant drive in a straight path between every landmark driving car has some limitations that to stay on road. Here the aim is to find the shortest route by the roads between every landmarks. The route which we used to obtain by searching in google maps, the same procedure is done here. But this time we needed to look up 2,450 directions to get the “true” distance between all 50 landmarks which has to be done handy. The google maps API makes the information available for free, so a python script is needed to calculate the distance and also the time driven for all 2450 routes between the 50 landmarks.
The next step is to approach the route as a travelling salesman problem. We need to order the list of landmarks in a way that the total distance traveled between them is as small as possible if we have visited them in order. This means that finding the route that backtracks as little as possible, which will be difficult when visiting Florida and the Northeast.
So clearly a smarter solutions is needed if a better road trip is needed in our lifetime.the travelling salesman problem has been well studied over the years and there are many ways to solve this problem in a reasonable amount of time.if we just need only the absolute best route between all the landmarks, then we can use the genetic algorithms which is good enough for our purpose. Genetic algorithm looks at every possible solutions and starts with handful of random solutions. And tries continuously with these solutions.it tries something different from the current solutions and marks the best one until it cannot find a better solution more than that.
Software: anaconda – jypyter
Modules used :
- import pandas
- import numpy
- import random
- import google maps
Genetic algorithms are adaptive heuristic search algorithms which belong to the larger part of evolutionary algorithms. It is based on the ideas of natural selection and genetics. The genetic algorithm uses random search which has hand full of solutions which is provided with historical data which directs the search into a better performance in solution space. This algorithm is mainly used to generate high quality solutions for optimization problems and search problems.This algorithm stimulates the process of natural selection.