TeamHOI：学习面向任意团队规模协作式人-物交互的统一策略
TeamHOI: Learning a Unified Policy for Cooperative Human-Object Interactions with Any Team Size
用 Transformer 加队友 token 的分散式策略处理可变团队规模协作，以及用单人参考动作加掩码 AMP 在缺少多智能体数据时保证动作真实感，这两点可直接迁移到视觉驱动的具身多智能体控制与动作生成。
原文依据 a Transformer-based policy network with teammate tokens, allowing scalable coordination across variable team sizes
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论基于物理的人形控制已在实现逼真且高性能的单智能体行为方面取得显著进展，但将这些能力扩展到协作式人-物交互（HOI）仍然具有挑战性。我们提出 TeamHOI，一个使单一分散式策略能够处理任意数量协作智能体之间协作式 HOI 的框架。每个智能体使用局部观测运行，同时通过带有队友 token 的 Transformer 策略网络关注其他队友，从而在可变团队规模下实现可扩展的协调。为在缓解协作式 HOI 数据稀缺的同时保证动作真实感，我们进一步引入掩码对抗运动先验（AMP）策略，在训练中使用单人参考动作，同时对与物体交互的身体部位进行掩码。掩码区域随后通过任务奖励进行引导，以产生多样且物理上合理的协作行为。我们在一个涉及二至八个人形智能体且物体几何形状各异的具有挑战性的协作搬运任务上评估 TeamHOI。最后，为促进稳定搬运，我们设计了一个与团队规模和形状无关的队形奖励。TeamHOI 取得了高成功率，并以单一策略在多种配置下展现出连贯的协作。
英文原文摘要 1307 字符
Physics-based humanoid control has achieved remarkable progress in enabling realistic and high-performing single-agent behaviors, yet extending these capabilities to cooperative human-object interaction (HOI) remains challenging. We present TeamHOI, a framework that enables a single decentralized policy to handle cooperative HOIs across any number of cooperating agents. Each agent operates using local observations while attending to other teammates through a Transformer-based policy network with teammate tokens, allowing scalable coordination across variable team sizes. To enforce motion realism while addressing the scarcity of cooperative HOI data, we further introduce a masked Adversarial Motion Prior (AMP) strategy that uses single-human reference motions while masking object-interacting body parts during training. The masked regions are then guided through task rewards to produce diverse and physically plausible cooperative behaviors. We evaluate TeamHOI on a challenging cooperative carrying task involving two to eight humanoid agents and varied object geometries. Finally, to promote stable carrying, we design a team-size- and shape-agnostic formation reward. TeamHOI achieves high success rates and demonstrates coherent cooperation across diverse configurations with a single policy.