지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술대회자료
- 저자정보
- 발행연도
- 2024.10
- 수록면
- 319 - 324 (6page)
이용수
초록· 키워드
오류제보하기
A new challenging area of research in autonomous systems focuses on the collaborative multi-agent exploration of unknown environments where a reliable communication infrastructure among the robotic platforms is absent. Factors like the proximity between agents, the characteristics of the network nodes, and environmental conditions can significantly impact data transmission in real-world applications. We present a novel decentralized collaborative architecture based on multi-agent reinforcement learning to address this challenge. In this framework, homogeneous agents autonomously decide to communicate or not, that is whether to share locally collected maps with other agents in the same communication networks or to navigate and explore the environment further. The agents’ policies are trained using the heterogeneousagent proximal policy optimization (HAPPO) algorithm and through a novel reward function that balances inter-agent communication and exploratory behaviors. The proposed architecture enhances mapping efficiency and robustness while minimizing inter-agent redundant data transmission. Finally, this paper demonstrates the advantages of the investigated approach compared to a strategy that does not incentivize communicative behaviors.
목차
Abstract
1. INTRODUCTION
2. METHODOLOGY
3. SIMULATION EXPERIMENTS
4. CONCLUSIONS
REFERENCES
참고문헌 (0)
참고문헌 신청함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
Generating Multi-agent Patrol Areas by Reinforcement Learning
제어로봇시스템학회 국제학술대회 논문집
2021 .10
-
멀티 에이전트 강화학습에서의 게이트 기반 메시지 교환
제어로봇시스템학회 논문지
2023 .11
-
Consensus speed of multi-agent systems driven by simultaneously fair value exchange
제어로봇시스템학회 국제학술대회 논문집
2024 .10
-
3가 티타늄을 환원제로 하는 무전해 주석도금
한국표면공학회 학술발표회 초록집
2016 .05
-
Multi-agent Reinforcement Learning in a Large Scale Environment via Supervisory Network and Curriculum Learning
제어로봇시스템학회 국제학술대회 논문집
2021 .10
-
Meta Multi-agent Reinforcement Learning for UAVs-aided IoT Networks: Initial Work
한국통신학회 학술대회논문집
2022 .02
-
Flocking Control for Multiple Polygonal Agents with Limited Communication Ranges
전기학회논문지
2019 .07
-
강화 학습 에이전트의 개성 부여를 유도하는 내재적 보상 방법 연구
대한전자공학회 학술대회
2022 .06
-
Cooperative Multi-Agent Reinforcement Learning for Global Reward
대한산업공학회 추계학술대회 논문집
2018 .11
-
A Study of Collaborative and Distributed Multi-agent Path-planning using Reinforcement Learning
한국컴퓨터정보학회논문지
2021 .03
-
희소 보상 환경 개선을 위한 정책 기반 심층 강화학습
전기학회논문지
2021 .03
-
Comparison of Multi-Agent Reinforcement Learning Algorithms in Cooperative Grid Environments
한국정보과학회 학술발표논문집
2024 .06
-
Multi-agent system의 Consensus에 대해 알아보자
제어로봇시스템학회지
2019 .12
-
Autonomous Drone Surveillance in a Known Environment Using Reinforcement Learning
제어로봇시스템학회 국제학술대회 논문집
2022 .11
-
Crowd Simulation Based on Statistical Analysis of Surveillance Video
한국방송미디어공학회 학술발표대회 논문집
2024 .11
-
Attention-Based Randomized Ensemble Multi-Agent Q-Learning
제어로봇시스템학회 국제학술대회 논문집
2023 .10
-
Autonomous and Asynchronous Triggered Agent Exploratory Path-planning Via a Terrain Clutter-index using Reinforcement Learning
Journal of information and communication convergence engineering
2022 .09
-
Multi-agent system에서의 dynamic edge란 무엇일까?
제어로봇시스템학회지
2020 .12
-
Robotic Navigation using Entropy-Based Exploration
제어로봇시스템학회 국제학술대회 논문집
2019 .10
-
자율 다개체 로봇의 작업관리
Proceedings of KIIT Conference
2022 .06
최근 본 자료
댓글(0)
0