GPS navigators are now present in most vehicles and smartphones. The usual goal of these navigators is to take the user in less time or distance to a destination. However, the global use of navigators in a given city could lead to traffic jams as they have a highly biased preference for some streets. From a general point of view, spreading the traffic throughout the city could be a way of preventing jams and making a better use of public resources. We propose a way of calculating alternative routes to be assigned by these devices in order to foster a better use of the streets. Our experimentation involves maps from OpenStreetMap, real road traffic, and the microsimulator SUMO. We contribute to reducing travel times, greenhouse gas emissions, and fuel consumption. To analyze the sociological aspect of any innovation, we analyze the penetration (acceptance) rate which shows that our proposal is competitive even when just 10% of the drivers are using it.
http://doi.acm.org/10.1145/3071178.3071193
Computing New Optimized Routes for GPS Navigators Using Evolutionary Algorithms
1. COMPUTING NEW OPTIMIZED ROUTES
FOR GPS NAVIGATORS
USING EVOLUTIONARY ALGORITHMS
Daniel H. Stolfi
dhstolfi@lcc.uma.es
Enrique Alba
eat@lcc.uma.es
Departamento de Lenguajes y Ciencias de la Computación
University of Malaga
Genetic and Evolutionary Computation Conference
GECCO 2017
Berlin, Germany
July 2017
2. CONTENTS
1 INTRODUCTION
2 OUR PROPOSAL
3 RESULTS
4 CONCLUSIONS & FUTURE WORK
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 1 / 17
3. CONTENTS
1 INTRODUCTION
2 OUR PROPOSAL
3 RESULTS
4 CONCLUSIONS & FUTURE WORK
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 1 / 17
4. CONTENTS
1 INTRODUCTION
2 OUR PROPOSAL
3 RESULTS
4 CONCLUSIONS & FUTURE WORK
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 1 / 17
5. CONTENTS
1 INTRODUCTION
2 OUR PROPOSAL
3 RESULTS
4 CONCLUSIONS & FUTURE WORK
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 1 / 17
7. Introduction
Our Proposal
Results
Conclusions & Future Work
Road Traffic
GPS Navigators
INTRODUCTION
Nowadays in our cities. . .
There is a larger number of vehicles in the streets
The number of traffic jams is rising
Tons of greenhouse gases are emitted to the
atmosphere
The citizens’ quality of life is decreasing
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 2 / 17
8. Introduction
Our Proposal
Results
Conclusions & Future Work
Road Traffic
GPS Navigators
INTRODUCTION
Nowadays in our cities. . .
There is a larger number of vehicles in the streets
The number of traffic jams is rising
Tons of greenhouse gases are emitted to the
atmosphere
The citizens’ quality of life is decreasing
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 2 / 17
9. Introduction
Our Proposal
Results
Conclusions & Future Work
Road Traffic
GPS Navigators
INTRODUCTION
Nowadays in our cities. . .
There is a larger number of vehicles in the streets
The number of traffic jams is rising
Tons of greenhouse gases are emitted to the
atmosphere
The citizens’ quality of life is decreasing
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 2 / 17
10. Introduction
Our Proposal
Results
Conclusions & Future Work
Road Traffic
GPS Navigators
INTRODUCTION
Nowadays in our cities. . .
There is a larger number of vehicles in the streets
The number of traffic jams is rising
Tons of greenhouse gases are emitted to the
atmosphere
The citizens’ quality of life is decreasing
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 2 / 17
11. Introduction
Our Proposal
Results
Conclusions & Future Work
Road Traffic
GPS Navigators
INTRODUCTION
Nowadays in our cities. . .
There is a larger number of vehicles in the streets
The number of traffic jams is rising
Tons of greenhouse gases are emitted to the
atmosphere
The citizens’ quality of life is decreasing
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 2 / 17
12. Introduction
Our Proposal
Results
Conclusions & Future Work
Road Traffic
GPS Navigators
GPS NAVIGATORS
Fixed routes
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 3 / 17
13. Introduction
Our Proposal
Results
Conclusions & Future Work
Road Traffic
GPS Navigators
GPS NAVIGATORS
Fixed routes
Shortest vs. fastest routes
Avenues, main streets, . . .
Everyone is taking the same (fast?) route
Some of them use traffic data
Internet? Expensive? Developing world?
Traffic jams
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 3 / 17
14. Introduction
Our Proposal
Results
Conclusions & Future Work
Road Traffic
GPS Navigators
GPS NAVIGATORS
Fixed routes
Shortest vs. fastest routes
Avenues, main streets, . . .
Everyone is taking the same (fast?) route
Some of them use traffic data
Internet? Expensive? Developing world?
Traffic jams
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 3 / 17
15. Introduction
Our Proposal
Results
Conclusions & Future Work
Road Traffic
GPS Navigators
GPS NAVIGATORS
Fixed routes
Shortest vs. fastest routes
Avenues, main streets, . . .
Everyone is taking the same (fast?) route
Some of them use traffic data
Internet? Expensive? Developing world?
Traffic jams
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 3 / 17
16. Introduction
Our Proposal
Results
Conclusions & Future Work
Road Traffic
GPS Navigators
GPS NAVIGATORS
Fixed routes
Shortest vs. fastest routes
Avenues, main streets, . . .
Everyone is taking the same (fast?) route
Some of them use traffic data
Internet? Expensive? Developing world?
Traffic jams
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 3 / 17
17. Introduction
Our Proposal
Results
Conclusions & Future Work
Road Traffic
GPS Navigators
GPS NAVIGATORS
Fixed routes
Shortest vs. fastest routes
Avenues, main streets, . . .
Everyone is taking the same (fast?) route
Some of them use traffic data
Internet? Expensive? Developing world?
Traffic jams
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 3 / 17
18. Introduction
Our Proposal
Results
Conclusions & Future Work
Road Traffic
GPS Navigators
GPS NAVIGATORS
Fixed routes
Shortest vs. fastest routes
Avenues, main streets, . . .
Everyone is taking the same (fast?) route
Some of them use traffic data
Internet? Expensive? Developing world?
Traffic jams
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 3 / 17
19. Introduction
Our Proposal
Results
Conclusions & Future Work
Road Traffic
GPS Navigators
GPS NAVIGATORS
Fixed routes
Shortest vs. fastest routes
Avenues, main streets, . . .
Everyone is taking the same (fast?) route
Some of them use traffic data
Internet? Expensive? Developing world?
Traffic jams
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 3 / 17
20. Introduction
Our Proposal
Results
Conclusions & Future Work
Alternative Routes
Case Study: Malaga
Evolutionary Algorithm
ALTERNATIVE ROUTES FOR GPS NAVIGATORS
Alternative routes to prevent traffic jams
For vehicles driving throughout the city
Reduce travel times
Reduce greenhouse gas emissions
Reduce fuel consumption
Save money
Improve health and
quality of life
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 4 / 17
21. Introduction
Our Proposal
Results
Conclusions & Future Work
Alternative Routes
Case Study: Malaga
Evolutionary Algorithm
ALTERNATIVE ROUTES FOR GPS NAVIGATORS
Alternative routes to prevent traffic jams
For vehicles driving throughout the city
Reduce travel times
Reduce greenhouse gas emissions
Reduce fuel consumption
Save money
Improve health and
quality of life
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 4 / 17
22. Introduction
Our Proposal
Results
Conclusions & Future Work
Alternative Routes
Case Study: Malaga
Evolutionary Algorithm
ALTERNATIVE ROUTES FOR GPS NAVIGATORS
Alternative routes to prevent traffic jams
For vehicles driving throughout the city
Reduce travel times
Reduce greenhouse gas emissions
Reduce fuel consumption
Save money
Improve health and
quality of life
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 4 / 17
23. Introduction
Our Proposal
Results
Conclusions & Future Work
Alternative Routes
Case Study: Malaga
Evolutionary Algorithm
ALTERNATIVE ROUTES FOR GPS NAVIGATORS
Alternative routes to prevent traffic jams
For vehicles driving throughout the city
Reduce travel times
Reduce greenhouse gas emissions
Reduce fuel consumption
Save money
Improve health and
quality of life
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 4 / 17
24. Introduction
Our Proposal
Results
Conclusions & Future Work
Alternative Routes
Case Study: Malaga
Evolutionary Algorithm
CALCULATING ALTERNATIVE ROUTES
Based on the Dynamic User Equilibrium (DUE)
Different probabilities for each route
Strategies:
Dijkstra
DUE.r
DUE.rp
DUE.ea
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 5 / 17
25. Introduction
Our Proposal
Results
Conclusions & Future Work
Alternative Routes
Case Study: Malaga
Evolutionary Algorithm
CALCULATING ALTERNATIVE ROUTES
Based on the Dynamic User Equilibrium (DUE)
Different probabilities for each route
Strategies:
Dijkstra
DUE.r
DUE.rp
DUE.ea
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 5 / 17
26. Introduction
Our Proposal
Results
Conclusions & Future Work
Alternative Routes
Case Study: Malaga
Evolutionary Algorithm
CALCULATING ALTERNATIVE ROUTES
Based on the Dynamic User Equilibrium (DUE)
Different probabilities for each route
Strategies:
Dijkstra
DUE.r
DUE.rp
DUE.ea
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 5 / 17
27. Introduction
Our Proposal
Results
Conclusions & Future Work
Alternative Routes
Case Study: Malaga
Evolutionary Algorithm
CALCULATING ALTERNATIVE ROUTES
Based on the Dynamic User Equilibrium (DUE)
Different probabilities for each route
Strategies:
Dijkstra
DUE.r
DUE.rp
DUE.ea
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 5 / 17
28. Introduction
Our Proposal
Results
Conclusions & Future Work
Alternative Routes
Case Study: Malaga
Evolutionary Algorithm
CALCULATING ALTERNATIVE ROUTES
Based on the Dynamic User Equilibrium (DUE)
Different probabilities for each route
Strategies:
Dijkstra
DUE.r
DUE.rp
DUE.ea
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 5 / 17
29. Introduction
Our Proposal
Results
Conclusions & Future Work
Alternative Routes
Case Study: Malaga
Evolutionary Algorithm
CALCULATING ALTERNATIVE ROUTES
Based on the Dynamic User Equilibrium (DUE)
Different probabilities for each route
Strategies:
Dijkstra
DUE.r
DUE.rp
DUE.ea
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 5 / 17
30. Introduction
Our Proposal
Results
Conclusions & Future Work
Alternative Routes
Case Study: Malaga
Evolutionary Algorithm
MALAGA CITY CENTER
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 6 / 17
31. Introduction
Our Proposal
Results
Conclusions & Future Work
Alternative Routes
Case Study: Malaga
Evolutionary Algorithm
MALAGA CITY CENTER
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 6 / 17
32. Introduction
Our Proposal
Results
Conclusions & Future Work
Alternative Routes
Case Study: Malaga
Evolutionary Algorithm
MALAGA CITY CENTER
OpenStreetMap
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 6 / 17
33. Introduction
Our Proposal
Results
Conclusions & Future Work
Alternative Routes
Case Study: Malaga
Evolutionary Algorithm
MALAGA CITY CENTER
OpenStreetMap SUMO
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 6 / 17
34. Introduction
Our Proposal
Results
Conclusions & Future Work
Alternative Routes
Case Study: Malaga
Evolutionary Algorithm
BUILDING MALAGA
1 Download the map from OpenStreetMap
2 Clean the irrelevant elements using JOSM
3 Import the city model using NETCONVERT
4 Define its routes using DUAROUTER and the Flow
Generator Algorithm (FGA)
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 7 / 17
35. Introduction
Our Proposal
Results
Conclusions & Future Work
Alternative Routes
Case Study: Malaga
Evolutionary Algorithm
BUILDING MALAGA
1 Download the map from OpenStreetMap
2 Clean the irrelevant elements using JOSM
3 Import the city model using NETCONVERT
4 Define its routes using DUAROUTER and the Flow
Generator Algorithm (FGA)
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 7 / 17
36. Introduction
Our Proposal
Results
Conclusions & Future Work
Alternative Routes
Case Study: Malaga
Evolutionary Algorithm
BUILDING MALAGA
1 Download the map from OpenStreetMap
2 Clean the irrelevant elements using JOSM
3 Import the city model using NETCONVERT
4 Define its routes using DUAROUTER and the Flow
Generator Algorithm (FGA)
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 7 / 17
37. Introduction
Our Proposal
Results
Conclusions & Future Work
Alternative Routes
Case Study: Malaga
Evolutionary Algorithm
BUILDING MALAGA
1 Download the map from OpenStreetMap
2 Clean the irrelevant elements using JOSM
3 Import the city model using NETCONVERT
4 Define its routes using DUAROUTER and the Flow
Generator Algorithm (FGA)
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 7 / 17
38. Introduction
Our Proposal
Results
Conclusions & Future Work
Alternative Routes
Case Study: Malaga
Evolutionary Algorithm
BUILDING MALAGA
1 Download the map from OpenStreetMap
2 Clean the irrelevant elements using JOSM
3 Import the city model using NETCONVERT
4 Define its routes using DUAROUTER and the Flow
Generator Algorithm (FGA)
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 7 / 17
39. Introduction
Our Proposal
Results
Conclusions & Future Work
Alternative Routes
Case Study: Malaga
Evolutionary Algorithm
CHARACTERISTICS OF THE CASE STUDY
3 km2
58 traffic lights
107 routes
More than 4800 vehicles per hour
Flows calculated using the Flow Generator Algorithm1
12 traffic measurement points
Working days, Saturdays, and Sundays
1
Daniel H Stolfi and Enrique Alba. “An Evolutionary Algorithm to Generate Real Urban Traffic Flows”. In:
Advances in Artificial Intelligence. Vol. 9422. Lecture Notes in Computer Science. Springer International Publishing,
2015, pp. 332–343.
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 8 / 17
40. Introduction
Our Proposal
Results
Conclusions & Future Work
Alternative Routes
Case Study: Malaga
Evolutionary Algorithm
CHARACTERISTICS OF THE CASE STUDY
3 km2
58 traffic lights
107 routes
More than 4800 vehicles per hour
Flows calculated using the Flow Generator Algorithm1
12 traffic measurement points
Working days, Saturdays, and Sundays
1
Daniel H Stolfi and Enrique Alba. “An Evolutionary Algorithm to Generate Real Urban Traffic Flows”. In:
Advances in Artificial Intelligence. Vol. 9422. Lecture Notes in Computer Science. Springer International Publishing,
2015, pp. 332–343.
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 8 / 17
41. Introduction
Our Proposal
Results
Conclusions & Future Work
Alternative Routes
Case Study: Malaga
Evolutionary Algorithm
CHARACTERISTICS OF THE CASE STUDY
3 km2
58 traffic lights
107 routes
More than 4800 vehicles per hour
Flows calculated using the Flow Generator Algorithm1
12 traffic measurement points
Working days, Saturdays, and Sundays
1
Daniel H Stolfi and Enrique Alba. “An Evolutionary Algorithm to Generate Real Urban Traffic Flows”. In:
Advances in Artificial Intelligence. Vol. 9422. Lecture Notes in Computer Science. Springer International Publishing,
2015, pp. 332–343.
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 8 / 17
42. Introduction
Our Proposal
Results
Conclusions & Future Work
Alternative Routes
Case Study: Malaga
Evolutionary Algorithm
EVOLUTIONARY ALGORITHM
(10+2)-EA
Individuals are evaluated using SUMO
Detours are implemented by using TraCI
Calculates the probability of each route (DUE.ea)
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 9 / 17
43. Introduction
Our Proposal
Results
Conclusions & Future Work
Alternative Routes
Case Study: Malaga
Evolutionary Algorithm
EVOLUTIONARY ALGORITHM
(10+2)-EA
Individuals are evaluated using SUMO
Detours are implemented by using TraCI
Calculates the probability of each route (DUE.ea)
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 9 / 17
44. Introduction
Our Proposal
Results
Conclusions & Future Work
Alternative Routes
Case Study: Malaga
Evolutionary Algorithm
REPRESENTATION
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 10 / 17
45. Introduction
Our Proposal
Results
Conclusions & Future Work
Alternative Routes
Case Study: Malaga
Evolutionary Algorithm
REPRESENTATION
121 probability values
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 10 / 17
46. Introduction
Our Proposal
Results
Conclusions & Future Work
Alternative Routes
Case Study: Malaga
Evolutionary Algorithm
REPRESENTATION
121 probability values
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 10 / 17
47. Introduction
Our Proposal
Results
Conclusions & Future Work
Alternative Routes
Case Study: Malaga
Evolutionary Algorithm
REPRESENTATION
121 probability values
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 10 / 17
48. Introduction
Our Proposal
Results
Conclusions & Future Work
Alternative Routes
Case Study: Malaga
Evolutionary Algorithm
EVALUATION
Fitness Function
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 11 / 17
49. Introduction
Our Proposal
Results
Conclusions & Future Work
Alternative Routes
Case Study: Malaga
Evolutionary Algorithm
EVALUATION
Fitness Function
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 11 / 17
50. Introduction
Our Proposal
Results
Conclusions & Future Work
Alternative Routes
Case Study: Malaga
Evolutionary Algorithm
EVALUATION
Fitness Function
F =
α
N
N
i=1
travel timei
We are minimizing travel times, so the lower the better
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 11 / 17
51. Introduction
Our Proposal
Results
Conclusions & Future Work
Alternative Routes
Case Study: Malaga
Evolutionary Algorithm
EVALUATION
Fitness Function
F =
α
N
N
i=1
travel timei
We are minimizing travel times, so the lower the better
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 11 / 17
58. Introduction
Our Proposal
Results
Conclusions & Future Work
Improvements
Examples
Penetration Rate
PREVENTING TRAFFIC JAMS
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 13 / 17
59. Introduction
Our Proposal
Results
Conclusions & Future Work
Improvements
Examples
Penetration Rate
BETTER ROUTES
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 14 / 17
60. Introduction
Our Proposal
Results
Conclusions & Future Work
Improvements
Examples
Penetration Rate
PENETRATION RATE
What if not all drivers are
using our proposal?
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 15 / 17
61. Introduction
Our Proposal
Results
Conclusions & Future Work
Improvements
Examples
Penetration Rate
PENETRATION RATE
What if not all drivers are using our proposal?
Penetration Rate Study
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 15 / 17
62. Introduction
Our Proposal
Results
Conclusions & Future Work
Improvements
Examples
Penetration Rate
PENETRATION RATE
What if not all drivers are using our proposal?
Penetration Rate Study
Working Days
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 15 / 17
63. Introduction
Our Proposal
Results
Conclusions & Future Work
Improvements
Examples
Penetration Rate
PENETRATION RATE
What if not all drivers are using our proposal?
Penetration Rate Study
Working Days Saturdays
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 15 / 17
64. Introduction
Our Proposal
Results
Conclusions & Future Work
Improvements
Examples
Penetration Rate
PENETRATION RATE
What if not all drivers are using our proposal?
Penetration Rate Study
Working Days Saturdays Sundays
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 15 / 17
65. Introduction
Our Proposal
Results
Conclusions & Future Work
Conclusions
Future Work
CONCLUSIONS
Alternative routes for GPS navigators
Based on the Dynamic User Equilibrium
Suggested according to probabilities (DUE.ea)
Scenarios based on real road traffic data (FGA)
DUE.ea achieved:
Shorter travel times (up to 18%)
Less greenhouse gas emissions (up to 14%)
Fuel saving (up to 7.5%)
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 16 / 17
66. Introduction
Our Proposal
Results
Conclusions & Future Work
Conclusions
Future Work
CONCLUSIONS
Alternative routes for GPS navigators
Based on the Dynamic User Equilibrium
Suggested according to probabilities (DUE.ea)
Scenarios based on real road traffic data (FGA)
DUE.ea achieved:
Shorter travel times (up to 18%)
Less greenhouse gas emissions (up to 14%)
Fuel saving (up to 7.5%)
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 16 / 17
67. Introduction
Our Proposal
Results
Conclusions & Future Work
Conclusions
Future Work
CONCLUSIONS
Alternative routes for GPS navigators
Based on the Dynamic User Equilibrium
Suggested according to probabilities (DUE.ea)
Scenarios based on real road traffic data (FGA)
DUE.ea achieved:
Shorter travel times (up to 18%)
Less greenhouse gas emissions (up to 14%)
Fuel saving (up to 7.5%)
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 16 / 17
68. Introduction
Our Proposal
Results
Conclusions & Future Work
Conclusions
Future Work
CONCLUSIONS
Alternative routes for GPS navigators
Based on the Dynamic User Equilibrium
Suggested according to probabilities (DUE.ea)
Scenarios based on real road traffic data (FGA)
DUE.ea achieved:
Shorter travel times (up to 18%)
Less greenhouse gas emissions (up to 14%)
Fuel saving (up to 7.5%)
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 16 / 17
69. Introduction
Our Proposal
Results
Conclusions & Future Work
Conclusions
Future Work
CONCLUSIONS
Alternative routes for GPS navigators
Based on the Dynamic User Equilibrium
Suggested according to probabilities (DUE.ea)
Scenarios based on real road traffic data (FGA)
DUE.ea achieved:
Shorter travel times (up to 18%)
Less greenhouse gas emissions (up to 14%)
Fuel saving (up to 7.5%)
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 16 / 17
70. Introduction
Our Proposal
Results
Conclusions & Future Work
Conclusions
Future Work
CONCLUSIONS
Alternative routes for GPS navigators
Based on the Dynamic User Equilibrium
Suggested according to probabilities (DUE.ea)
Scenarios based on real road traffic data (FGA)
DUE.ea achieved:
Shorter travel times (up to 18%)
Less greenhouse gas emissions (up to 14%)
Fuel saving (up to 7.5%)
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 16 / 17
71. Introduction
Our Proposal
Results
Conclusions & Future Work
Conclusions
Future Work
CONCLUSIONS
Alternative routes for GPS navigators
Based on the Dynamic User Equilibrium
Suggested according to probabilities (DUE.ea)
Scenarios based on real road traffic data (FGA)
DUE.ea achieved:
Shorter travel times (up to 18%)
Less greenhouse gas emissions (up to 14%)
Fuel saving (up to 7.5%)
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 16 / 17
72. Introduction
Our Proposal
Results
Conclusions & Future Work
Conclusions
Future Work
CONCLUSIONS
Alternative routes for GPS navigators
Based on the Dynamic User Equilibrium
Suggested according to probabilities (DUE.ea)
Scenarios based on real road traffic data (FGA)
DUE.ea achieved:
Shorter travel times (up to 18%)
Less greenhouse gas emissions (up to 14%)
Fuel saving (up to 7.5%)
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 16 / 17
73. Introduction
Our Proposal
Results
Conclusions & Future Work
Conclusions
Future Work
CONCLUSIONS
Alternative routes for GPS navigators
Based on the Dynamic User Equilibrium
Suggested according to probabilities (DUE.ea)
Scenarios based on real road traffic data (FGA)
DUE.ea achieved:
Shorter travel times (up to 18%)
Less greenhouse gas emissions (up to 14%)
Fuel saving (up to 7.5%)
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 16 / 17
74. Introduction
Our Proposal
Results
Conclusions & Future Work
Conclusions
Future Work
FUTURE WORK
Extend our analysis to other/bigger areas
Optimization of the entire city by districts/neighborhoods
Address the simulation of thousands of vehicles
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 17 / 17
75. Introduction
Our Proposal
Results
Conclusions & Future Work
Conclusions
Future Work
FUTURE WORK
Extend our analysis to other/bigger areas
Optimization of the entire city by districts/neighborhoods
Address the simulation of thousands of vehicles
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 17 / 17
76. Introduction
Our Proposal
Results
Conclusions & Future Work
Conclusions
Future Work
FUTURE WORK
Extend our analysis to other/bigger areas
Optimization of the entire city by districts/neighborhoods
Address the simulation of thousands of vehicles
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 17 / 17
77. Introduction
Our Proposal
Results
Conclusions & Future Work
Conclusions
Future Work
FUTURE WORK
Extend our analysis to other/bigger areas
Optimization of the entire city by districts/neighborhoods
Address the simulation of thousands of vehicles
Daniel H. Stolfi & Enrique Alba Computing New Optimized Routes for GPS. . . 17 / 17
78. QUESTIONS
Computing New Optimized Routes for GPS Navigators
Using Evolutionary Algorithms
Questions?
Daniel H. Stolfi Enrique Alba
dhstolfi@lcc.uma.es eat@lcc.uma.es
http://danielstolfi.com http://neo.lcc.uma.es
Acknowledgements: This research has been partially funded by Spanish MINECO project TIN2014-57341-R (moveON). Daniel H. Stolfi is
supported by a FPU grant (FPU13/00954) from the Spanish Ministry of Education, Culture and Sports. University of Malaga. International
Campus of Excellence Andalucia TECH.