Sanjaya, Steven Willy (2019) Penerapan Naïve Bayes Untuk NPC Braking Decision Pada Racing Game. Sarjana thesis, Universitas Brawijaya.
Abstract
Racing game merupakan salah satu game yang masih populer hingga saat ini. Pada perkembangannya selalu tidak lepas dari dibutuhkannya NPC (Non-Player Character). NPC yang hadir sebagai lawan main dari pemain selalu dihadapkan dengan permasalahan bagaimana membuat NPC yang cerdas. Salah satu permasalahannya adalah braking decision yaitu kapan NPC harus mengurangi kecepatannya dengan menggunakan rem. Salah satu metode yang umum digunakan adalah brake zone, namun metode tersebut kurang efektif karena harus memasang zone secara manual di setiap tikungan yang dibutuhkan. Solusi lain seperti Smart AI System pada Racing Game Starter Kit (RGSK) kurang efektif karena diperlukan konfigurasi yang tepat untuk memperoleh hasil yang optimal. Untuk mengatasi masalah tersebut peneliti menerapkan metode machine learning yaitu Naïve Bayes dalam braking decision. Naïve Bayes menggunakan tiga fitur untuk masukan dan dua kelas keluaran yang data latihnya diperoleh dari pemain. Hasil pengujian menunjukkan bahwa hasil braking decision dari Naïve Bayes mampu membuat kendaraan tidak menabrak pembatas di luar lintasan tanpa menurunkan FPS (Frames per Second) dari game. Perolehan waktu setiap lap dari Naïve Bayes mampu mengungguli Smart AI System dengan tingkat kesulitan hard dengan rata-rata 5,44 detik lebih cepat selama 10 lap.
English Abstract
Racing is a video game genre that is still popular today. Its development processes cannot be separated from the need to have Non-Player Character (NPC) in them. NPCs act as the opponents for the players, and thus the developers are always challenged with the problem of how to make the NPCs smarter than them. One of the problems is related with breaking decision, or when the NPCs decided to slow down their speed during races by using brakes. One commonly used method for this type of experiment is the Brake Zone. Although, this method also has its own shortcomings, such as the devs have to manually place the zone themselves in the designated locations for the brake test. Other solution that can be applied is Smart AI System by Racing Game Starter Kit (RGSK), but this also has its problem in which to get the best result, a proper configuration is needed. To resolve the problem, researcher proposes the method of machine learning, Naïve Bayes for the braking decision. Naïve Bayes use three features for the data input, and two output class in which the data will be obtained from the player. The test result showed that the braking decision from Naïve Bayes was able to prevent the vehicle from crashing with the outer wall without dropping the game’s FPS (Frames per Second). Naïve Bayes’s lap time also surpass Smart AI System hard level with average 5.44 second better through 10 lap.
| Item Type: | Thesis (Sarjana) |
|---|---|
| Identification Number: | SKR/FILKOM/2019/14/051902184 |
| Uncontrolled Keywords: | Racing Game, Naïve Bayes, Braking Decision, NPC |
| Subjects: | 700 The Arts > 796 Athletic and outdoor sports and games |
| Divisions: | Fakultas Ilmu Komputer > Teknik Informatika |
| Depositing User: | soegeng sugeng |
| Date Deposited: | 22 Jul 2020 04:46 |
| Last Modified: | 19 Oct 2021 09:33 |
| URI: | http://repository.ub.ac.id/id/eprint/168841 |
Preview |
Text
Steven Willy Sanjaya.pdf Download (2MB) | Preview |
Actions (login required)
 |
View Item |