The Journal of the Korea institute of electronic communication sciences (한국전자통신학회논문지)

Korea Institute of Electronic Communication Science (한국전자통신학회)
권호 표지
DOI QR코드

DOI QR Code

Automated PDDL Planning System using Graph Database

그래프 데이터베이스 기반 자동 PDDL Planning 시스템

  • Ji-Youn Moon (Dept. of Electronics Engineering, Chosun University)
  • 문지윤 (조선대학교 전자공학부)
  • Received : 2023.06.27
  • Accepted : 2023.08.17
  • Published : 2023.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

A flexible planning system is an important element for the robot to perform various tasks. In this paper, we introduce an automated planning system architecture that can deal with the changing environment. PDDL is used for symbolic-based task planning, and a graph database is used for real-time environment information updates for automated PDDL generation. The proposed framework was verified through scenario-based experiments.

유연한 planning system은 로봇이 다양한 임무를 수행하기 위해서 중요한 요소이다. 본 논문에서는 변화하는 환경에 대응할 수 있는 automated planning system architecture를 소개한다. 심볼릭 기반의 task planning을 위해 PDDL을 활용하였으며 실시간 환경 정보 업데이트를 위해 그래프 데이터베이스를 이용한다. 제안한 구조는 시나리오 기반 실험을 통해 검증하였다.

Keywords

Acknowledgement

이 논문은 2023학년도 조선대학교 학술연구비의 지원을 받아 연구되었음.

References

  1. Y. S. Moon, Y. C. Bae, H. R. Cha, , S. H. Roh, J. K. Park, "The Development of Ecobot Robot for Friendly Environment Smart Home Appliance Application System," The J. of the Korea Institute of Electronics Communications Sciences, vol. 5, no. 4, 2010, pp. 480-485.
  2. J. H. Bong, S. H. Lee, D. J. Koh, , N. B. Kim, E. S. Park, D. R. Jeon, " Mobile Robot for Indoor Air Quality Monitoring," The J. of the Korea Institute of Electronics Communications Sciences, vol. 17, no. 3, 2022, pp. 537-542.
  3. J. Fan, Z. Pai, L. Shufei, "Vision-based holistic scene understanding towards proactive human -robot collaboration," Robotics and Computer-Integrated Manufacturing vol. 75, pp. 102304, 2022.
  4. J. Moon, "Plugin Framework-Based Neuro-Symbolic Grounded Task Planning for Multi-Agent System," Sensors, vol. 21, no. 23, 2021, pp. 7896.
  5. S. Miglani, and N. Yorke-Smith, "Nltopddl: One-shot learning of pddl models from natural language process manuals," In ICAPS'20 Workshop on Knowledge Engineering for Planning and Scheduling, 2020.
  6. J. Moon, J. Moon, and S. Bea, "Control for Manipulator of an Underwater Robot Using Meta Reinforcement Learning," J. of the Korea Institute of Electronics Communications Sciences, vol. 16, no. 1, 2021, pp. 95-100.
  7. J. Fan, Z. Pai, and L. Shufei, "Vision-based holistic scene understanding towards proactive human-robot collaboration," Robotics and Computer-Integrated Manufacturing, vol. 75, 2022, pp. 102304.
  8. J. Webber, "A programmatic introduction to neo4j," In proceedings of the 3rd annual conference on Systems, programming, and applications: software for humanity, pp. 217-218, 2012.
  9. H. A. Geffner, "PDDL 2.1: Representation vs. computation," Journal of Artificial Intelligence Research, vol. 20, pp, 139-144,
  10. M.. Fox and D. Long. "PDDL2.1: An Extension to PDDL for Expressing Temporal Planning Domains," Journal of Artificial Intelligence Research, AI Access Foundation, December 1, 2003.