机器人技术与大型语言模型(LLM)的最新进展,引发了人们对人机协作和具身智能日益增长的兴趣。为使机器人能够更广泛地部署在有人活动的环境中,具有社会意识的机器人导航(SAN)已成为一个关键研究领域。尽管将人机交互(HRI)与路径规划相结合的深度强化学习方法已展现出强劲的基准性能,但它们往往难以适应新的场景和环境。LLM 通过常识推理为零样本导航提供了一条有前景的途径。然而,现有大多数基于 LLM 的框架依赖集中式决策,缺乏稳健的验证机制,并且在将宏观动作转化为精确底层控制信号时存在不一致性。为应对这些挑战,我们提出 SAMALM,这是一个用于多机器人社交导航的去中心化多智能体 LLM actor-critic 框架。在该框架中,一组并行的 LLM actor 直接生成控制信号,每个 actor 反映不同的机器人个性或配置。这些动作经过两级验证过程:由全局 critic 评估群体级行为,并由各个独立 critic 评估每个机器人的情境。基于熵的分数融合机制进一步增强自验证和重新查询,从而提升稳健性与协调性。实验结果证实,SAMALM 有效平衡了局部自主性与全局监督,在多种多机器人场景中产生符合社会规范的行为和强大的适应能力。有关本工作的更多细节和视频可在 https://sites.google.com/view/SAMALM 获取。
英文摘要:
Recent advances in robotics and large language models (LLMs) have sparked growing interest in human-robot collaboration and embodied intelligence. To enable the broader deployment of robots in human-populated environments, socially-aware robot navigation (SAN) has become a key research area. While deep reinforcement learning approaches that integrate human-robot interaction (HRI) with path planning have demonstrated strong benchmark performance, they often struggle to adapt to new scenarios and environments. LLMs offer a promising avenue for zero-shot navigation through commonsense inference. However, most existing LLM-based frameworks rely on centralized decision-making, lack robust verification mechanisms, and face inconsistencies in translating macro-actions into precise low-level control signals. To address these challenges, we propose SAMALM, a decentralized multi-agent LLM actor-critic framework for multi-robot social navigation. In this framework, a set of parallel LLM actors, each reflecting distinct robot personalities or configurations, directly generate control signals. These actions undergo a two-tier verification process via a global critic that evaluates group-level behaviors and individual critics that assess each robot's context. An entropy-based score fusion mechanism further enhances self-verification and re-query, improving both robustness and coordination. Experimental results confirm that SAMALM effectively balances local autonomy with global oversight, yielding socially compliant behaviors and strong adaptability across diverse multi-robot scenarios. More details and videos about this work are available at: https://sites.google.com/view/SAMALM.
Spiking Neural Network Actor-Critic Proximal Policy Optimization Control for Autonomous UAV Navigation Through Constrained Openings in Civil Infrastructure and Buildings
Alma Mater Europaea University(欧洲阿尔马马特大学);AGH University of Krakow(克拉科夫AGH科技大学)
Learning Object-conditioned Exploration using Distributed Soft Actor Critic
Robotics at Google(谷歌机器人部门)
对象导航被定义为在复杂的、未探索的环境中导航到给定标签的对象。在其一般形式中,这个问题给机器人技术带来了几个挑战:在搜索对象和低级控制时对未知环境进行语义探索。在这项工作中,我们研究了对象引导的探索和低级别的控制,并提出了一个端到端的训练导航策略,实现了0.68的成功率和0.58的SPL对看不见的,视觉上复杂的扫描真实的家园。我们提出了一种高度可扩展的非策略强化学习算法的实现,分布式Soft Actor Critic,它允许系统在8个GPU上在24小时内利用98M经验步骤。我们的系统学习控制差分驱动移动基地在模拟中,从机器人平台上常用的高维观测堆栈。学习的策略能够从现实环境中的纯经验中学习到对象引导的探索性行为和低级控制。
Mapless Navigation of a Hybrid Aerial Underwater Vehicle with Deep Reinforcement Learning Through Environmental Generalization
Universidad Tecnológica del Uruguay (UTEC)(乌拉圭技术大学);Centro de Ciências Computacionais (C3) of Universidade Federal do Rio Grande (FURG)(里奥格兰德联邦大学计算科学中心);Universidade Federal de Santa Maria (UFSM)(圣玛丽亚联邦大学)