论文标题
基于分层需求的合作多机器人系统的自适应框架
Hierarchical Needs Based Self-Adaptive Framework For Cooperative Multi-Robot System
论文作者
论文摘要
多机器人和群体系统中的研究对在复杂和动态环境中的代理合作有浓厚的兴趣。为了有效地适应未知环境并最大化小组的实用性，机器人需要根据特定情况进行合作，共享信息并制定合适的计划。受马斯洛的人类需求和系统理论等级制度的启发，我们介绍了机器人的需求层次结构，并提出了一种新的解决方案，称为自适应群体系统（SASS）。它通过分布式的谈判统计机制将多机构感知，沟通，计划和执行与冲突的合作管理相结合，该机制优先考虑机器人的需求。我们还通过多个原子操作（例如选择，形成和路由）将复杂的任务分解为简单的可执行行为。我们通过模拟静态和动态任务来评估SASS，并将其与集成到我们框架中的最新碰撞意识任务分配方法进行比较。
Research in multi-robot and swarm systems has seen significant interest in cooperation of agents in complex and dynamic environments. To effectively adapt to unknown environments and maximize the utility of the group, robots need to cooperate, share information, and make a suitable plan according to the specific scenario. Inspired by Maslow's hierarchy of human needs and systems theory, we introduce Robot's Need Hierarchy and propose a new solution called Self-Adaptive Swarm System (SASS). It combines multi-robot perception, communication, planning, and execution with the cooperative management of conflicts through a distributed Negotiation-Agreement Mechanism that prioritizes robot's needs. We also decompose the complex tasks into simple executable behaviors through several Atomic Operations, such as selection, formation, and routing. We evaluate SASS through simulating static and dynamic tasks and comparing them with the state-of-the-art collision-aware task assignment method integrated into our framework.
