Journal of the Semiconductor & Display Technology (반도체디스플레이기술학회지)

The Korean Society Of Semiconductor & Display Technology (한국반도체디스플레이기술학회)
권호 표지

Implementation of Target Object Tracking Method using Unity ML-Agent Toolkit

Unity ML-Agents Toolkit을 활용한 대상 객체 추적 머신러닝 구현

  • Han, Seok Ho (Korea Electronics Technology Institute, IT Application Research Center) ;
  • Lee, Yong-Hwan (Dept. of Digital Contents, Wonkwang University)
  • 한석호 (한국전자기술연구원 IT응용연구센터) ;
  • 이용환 (원광대학교 디지털콘텐츠공학과)
  • Received : 2022.09.14
  • Accepted : 2022.09.21
  • Published : 2022.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

Non-playable game character plays an important role in improving the concentration of the game and the interest of the user, and recently implementation of NPC with reinforcement learning has been in the spotlight. In this paper, we estimate an AI target tracking method via reinforcement learning, and implement an AI-based tracking agency of specific target object with avoiding traps through Unity ML-Agents Toolkit. The implementation is built in Unity game engine, and simulations are conducted through a number of experiments. The experimental results show that outstanding performance of the tracking target with avoiding traps is shown with good enough results.

Keywords

Acknowledgement

본 연구는 2022년도 정부(미래창조과학부)의 재원으로 한국연구재단의 지원을 받아 수행된 기초연구사업임(과제번호: 2021R1A2C1012947).

References

  1. Yerim Choi, Gwanho Kim, "Artificial Intelligence Overview and Application Examples", IE Magazine, Vol. 23, No. 2, pp. 23-29, Jun. 2016.
  2. Qiyue Yin, Jun Yang, Wancheng Ni, Bin Liang, Kaiqi Huang, "AI in Games: Techniques, Challenges and Opportunities", Journal of Latex Class Files, Vol.14, no.8, 2015.
  3. Soo-young Jang, et al., "Deep Reinforcement Learning Technology Trends", [ETRI] Electronic Communication Trend Analysis 34.4:1-14, 2019.
  4. Pedro J. Rivera Torres, Carlos Gershenson Garcia, Samir Kanaan Izquierdo, "Reinforcement Learning with Probabilistic Boolean Networks Models of Smart Grid Devices", DBLP Computer Science Bibliography, 2021.
  5. Unity ML-Agents Toolkit downloadable website: https://github.com/Unity-Technologies/ml-agents
  6. Unity Machine Learning Agents https://unity.com/products/machine-learning-agents
  7. Jo Myoung Kang, Young Hwa Cha, Byung Joon Park, "Implementation of 3D Game using NPC with Artificial Intelligence", The Institute of Electronics and Information Engineers Conference, 2018.
  8. Taeyeong Choi, Hyeon-Suk Na, "Making Levels More Challenging with a Cooperative Strategy of Ghosts in Pac-Man", Journal of Korea Game Society, Vol.15, No.5, 2015.
  9. Seongho Jeon, Hyongil Kim, Juntae Kim, Kyhyun Um, Hyungje Cho, "Priority-Based Collision Avoidance on a Navigation Mesh", Proceedings of the Korean Information Science Society Conference, Vol.31, No.1, 2004.
  10. Deokhyung Kim, Hyunjun Jun, "Performance Analysis of Target Tracking AI based on Unity ML-Agent", Journal of KIIT, Vol.19, No.12, 2021.
  11. Abhilash Majumder, "Deep Reinforcement Learning in Unity", Apress, 2020.
  12. Thomas H. Cormen, Charles E. Leiserson, Ronald L. Rivest, Clifford Stein, "Introduction to Algorithms 3E (CLRS)", MIT Press, 2018.
  13. Dong-Bin Choi, In-su Jo, Yong B. Park, "Taxation Analysis using Machine Learning", Journal of the Semiconductor & Display Technology, vol.18. no.2, 2019.
  14. Song-Yeon Lee, Yong Jeong Huh, "A Study on Surface Defect Detection Model of 3D Printing Bone Plate using Deep Learning Algorithm", Journal of the Semiconductor & Display Technology, vol.21. no.2, 2022.