Project Sample PPT

You might also like

Download as pptx, pdf, or txt
Download as pptx, pdf, or txt
You are on page 1of 19

G.H.

RAISONI INSTITUTE OF ENGINEERING AND


TECHNOLOGY, PUNE
Department of Artificial Intelligence

OPTIMIZED DRONE ROUTING SYSTEM


FOR DELIVERY MANAGEMENT

Name Of Projectees : Group ID: COMP_22-23_1


Project Guide: 1. Om Khade 3. Ishwari Gundawar
Prof . Rachana Sable 2. Samarth Chavan 4. Bhushan Kakade
Contents:

1. Introduction
2. Literature Survey
3. Problem Statement
4. Clear idea regarding existing &
proposed system
5. Objective
6. Proposed System Architecture &
Methodology.
7. System Design
8. Algorithm & GUI Implementation
9. Results & Discussion
10. Advantages & Disadvantages
11. Applications
12. Conclusion & Future Scope
13. References
INTRODUCTION

● With the rise of e-commerce, last-mile delivery has become a significant cost driver in the supply chain, with
traditional delivery methods proving to be time-consuming, labor-intensive, and costly. The use of drones for
last-mile delivery offers a promising solution, with the potential to deliver packages more efficiently and
cost-effectively.

● However, the effective routing and distribution of delivery jobs to a fleet of drones remains a significant
obstacle. This involves finding the most efficient routes for the drones to take, while also coordinating their
movements to ensure quick and safe package delivery.
LITERATURE SURVEY
Table 1 . Literature Survey
Literature Problem Addressed Contribution/ Modeling and Assumptions/ Limitations
Source Proposed Strategy Analyzing Method

Murray and Chu Hybrid delivery issue Seeks to coordinate a truck Mixed integer Linear No real data used, neither for
(2015) (drone +truck) optimal with a drone, Approach called programming formulations to drone characteristics nor for the
Assignments issue. “Truck First, Drone Second”. resolve Traveling Salesman logistic delivery operator.
Problem TSP and Parallel
machine Scheduling (PMS).

Jeon etal. (2021) Vehicle routing problem A routing model is proposed to Mixed integer linear Model did not consider
with drone and truck. optimize the cost, by reducing Programming based on energy and payload.
the empty flights. Murray and Chu model.

Dorlinget al .(2016) Multi-trip vehicle routing Deals with cost issue with a Mixed integer linear Limited size of the
problems. delivery time Constraint. programs (MILPs) to delivery
Optimize the delivery time minimize the costs. system
subject to a cost limit.

Wanget al. (2016) Multiple trucks with multi- The drone vehicle traffic Heuristic optimization. No use of real data and
drones. approach to serving all no use of autonomous
customers in the least amount drones
of time.
PROBLEM STATEMENT

Due to the substantial increase in the use of online ordering, there is a greater need for delivery employees. The last-
mile delivery component, which accounts for 30% of the total cost of the supply chain, is the biggest cost generator.

It is also one of the most time- and labor-intensive components of a delivery network. As a result, drone-based
delivery is the industry's next major advancement.

Solution to this problem statement is

1. Automate delivery Management System.


2. The hybrid algorithm minimizes distance traveled and maximizes delivery efficiency, while handling
capacity constraints and multiple objectives.
OBJECTIVE

To propose hybrid algorithm for drone delivery routing, which aims to optimize the delivery routes, reduce delivery
costs, and improve overall efficiency by developing a hybrid algorithm using Non-dominated Sorting Genetic
Algorithm II (NSGA-II), D'Andrea equation, and Capacitated Vehicle Routing Problem (CVRP) techniques.

By leveraging the strengths of these techniques, the hybrid algorithm will be able to generate optimized delivery
routes that take into account factors such as

● Drone speed
● Payload capacity
● Package delivery priorities
● Battery Life and Charging Stations
● Customer Locations
● Dynamic Updates
● Multi-Objective Optimization
NOVELTY

1. The hybrid algorithm that integrates different optimization techniques such as heuristic and meta-heuristic
algorithms to generate more efficient and effective delivery routes.
2. Considering drone range, payload capacity, and battery life to optimize the delivery routes.
3. Developed a environmentally sustainable solution which decrease the carbon footprint of drone delivery
4. Use of NSGA-II algorithm to generate multiple optimized solutions for delivery routes.

Fig 1. Hybrid Algorithm


SYSTEM ARCHITECTURE

Fig.2 System Architecture


VRP (Vehicle Routing Problem) CVRP ( Capicated Vehicle Routing
Problem)
VRP fundamentally the same as the Traveling CVRP is the fundamental adaptation of the VRP.
Salesman Problem (TSP) but has numerous
The goal of CVRP is to decide ideal route plan
limitations, for example, vehicle limit, time
which minimizes the distance or cost with the
window, multi-warehouses and others, which
accompanying requirements:
gives it more complicated settlement space.
● Each client is served precisely once by
precisely one vehicle
● Each vehicle begins and finishes its route at
the depot
● The aggregate length of each route should not
surpass the limitation
● The aggregate request of any route should not
surpass the capacity of the vehicle

Fig. 3 Vehicle Routing Problem


EXAMPLES: Flytrex

1. Amazon Prime Air


● Prime Air will deliver packages up to 5 pounds in
30 minutes or less using small drones. 2.Flytrex
● Amazon has been developing and testing the
● Flytrex offers an end-to-end delivery service
platform through Prime Air development centers
using automated drones for retailers, ecommerce
in the U.S., the U.K., Austria, France, and Israel.
● marketplaces, restaurants, and delivery
In August 2020, Amazon received approval from
companies.
the FAA to operate its Prime Air delivery drones
● Started in Israel in 2013 as a supplier for drone
to “safely and efficiently” deliver packages to
manufacturers, Flytrex became one of the first
customers.
● commercial drone operators, delivering groceries
In 2019, at the re:MARS conference, Amazon
and other goods in Reykjavik, Iceland.
unveiled its latest Prime Air drone design..
COMPARATIVE STUDY
Table 2. Comparative Analysis

Existing Proposed Systems Drawbacks of Existing System Efficiency,Advantages of Drone


Delivery Routing System

1. Amazon Prime Air Less Efficient in Battery Efficient Battery Consumptions


Management

2. FW logistic Security: Drones are being hacked Our Live tracking Algorithm
overcomes this
RESULTS
Table . 3 Evaluation matrix

Criteria Normal Delivery Drone Delivery Path Optimized

Delivery Cost $100 $45 :40% $27 : 73 %

Delivery Speed 8 hours (43%) 3 hours (55% Faster) 30 mins (80% Faster)
(single drone can deliver multiple parcels
using optimized path)

Range Coverage 150 miles 30 miles 30 miles

Payload Capacity - 5 kg 5 kg

Reliability High Moderate High(we are using live tracking & efficient
path)
ADVANTAGES
● Significant Cost Savings
● Environmental Benefits
● Improved Efficiency
● Increased Customer Satisfaction
● Scalability and Flexibility
● Safety and Risk Mitigation:
● Access to Remote Areas
● Lower Carbon Footprint
● Real-Time Tracking
● Competitive Advantage

DISADVANTAGES
● Current model for route optimization has no solution to handel on route compilations that might
occur
● GPS data can be inaccurate, which can have an impact on package drop points
DATABASE ARCHITECTURE

Fig 4. Database Architecture


OUTPUT RESULT

Fig.5 Output Result


APPLICATIONS
• The Drone Delivery Management System has a wide range of potential applications, including:

• Food Delivery: The system can be used to deliver food to customers in urban areas, eliminating the need for
drivers and reducing delivery times.

• Medical Supplies: Drones can be used to deliver medical supplies, such as vaccines and drugs, to remote or
hard-to-reach areas.

• E-commerce: Online retailers can use the system to deliver goods to customers in a timely and efficient
manner, even in congested urban areas.
CONCLUSION

Based on our satisfiability analysis and complexity assessment, we conclude that the proposed problem
statement for our Drone Routing System for Delivery Management project is feasible but challenging. It
requires the use of advanced mathematical models and algorithms to optimize the routing and distribution of
delivery jobs to a fleet of drones, and has the potential to significantly improve the efficiency and cost-
effectiveness of last-mile delivery while reducing the carbon footprint of the delivery industry.
PROJECT GUIDE:

PROF.RACHNA SABLE(HOD AI AND DS)

PROJECT BY

1.OM KHADE (24 B.Tech COMP)

2.SAMARTH CHAVAN(67 B.Tech COMP)

3.ISHWARI GUNDAWAR(64 B.Tech COMP)

4.BHUSHAN KAKADE(20 B.Tech COMP)


THANK YOU

You might also like