Zotos, Leonidas (2020) Using Auctions for Traffic Moderation in Road Intersections. Bachelor's Thesis, Artificial Intelligence.
|
Text
AI_BA_2020_LeonidasZotos.pdf Download (5MB) | Preview |
|
![[img]](https://fse.studenttheses.ub.rug.nl/style/images/fileicons/text.png) |
Text
toestemming.pdf Restricted to Registered users only Download (108kB) |
Abstract
A large portion of our everyday life is spent on the road traffic network during commutes. This has been linked to various poor health outcomes. To decrease the time spent on the road network, different measures have been taken (e.g. intelligent traffic lights). However, even state-of-the-art mechanisms do not take into consideration the individual urgency of drivers. To tackle this problem, auction-based approaches have been explored in the past. There, drivers waiting at a road intersection can place bids to receive priority for the use of the intersection. It was previously found that the utilisation of auctions for traffic moderation can lead to significantly reduced waiting times. However, an aspect that has not been sufficiently explored is the performance of different bidding strategies. In the current research, a multi-agent traffic network was set-up in which five different bidding strategies were tested. A number of simulations were run with varying distributions of present bidding strategies. At a single-agent level, the reinforcement-learning bidding strategy was found to perform best. However, using various measures, it was found that a traffic network only consisting of drivers that use adaptive bidding led to the best performing society.
| Item Type: | Thesis (Bachelor's Thesis) |
|---|---|
| Supervisor name: | Grossi, D. |
| Degree programme: | Artificial Intelligence |
| Thesis type: | Bachelor's Thesis |
| Language: | English |
| Date Deposited: | 01 Sep 2020 13:52 |
| Last Modified: | 01 Sep 2020 13:52 |
| URI: | https://fse.studenttheses.ub.rug.nl/id/eprint/23322 |
Actions (login required)
 |
View Item |