Recent years have seen significant advancements in humanoid control, largely due to the availability of large-scale motion capture data and the application of reinforcement learning methodologies. However, many real-world tasks, such as moving large and heavy furniture, require multi-character collaboration. Given the scarcity of data on multi-character collaboration and the efficiency challenges associated with multi-agent learning, these tasks cannot be straightforwardly addressed using training paradigms designed for single-agent scenarios. In this paper, we introduce Cooperative Human-Object Interaction (CooHOI), a novel framework that addresses multi-character objects transporting through a two-phase learning paradigm: individual skill acquisition and subsequent transfer. Initially, a single agent learns to perform tasks using the Adversarial Motion Priors (AMP) framework. Following this, the agent learns to collaborate with others by considering the shared dynamics of the manipulated object during parallel training using Multi Agent Proximal Policy Optimization (MAPPO). When one agent interacts with the object, resulting in specific object dynamics changes, the other agents learn to respond appropriately, thereby achieving implicit communication and coordination between teammates. Unlike previous approaches that relied on tracking-based methods for multi-character HOI, CooHOI is inherently efficient, does not depend on motion capture data of multi-character interactions, and can be seamlessly extended to include more participants and a wide range of object types

翻译：近年来，由于大规模运动捕捉数据的可用性以及强化学习方法的应用，仿人机器人控制取得了显著进展。然而，许多现实世界任务，例如移动大型重型家具，需要多角色协作。鉴于多角色协作数据的稀缺性以及与多智能体学习相关的效率挑战，这些任务无法直接使用为单智能体场景设计的训练范式来解决。本文提出了协作式人-物交互（CooHOI），这是一个新颖的框架，通过两阶段学习范式——个体技能获取与后续迁移——来解决多角色物体搬运问题。首先，单个智能体学习使用对抗性运动先验（AMP）框架执行任务。随后，该智能体通过在使用多智能体近端策略优化（MAPPO）进行并行训练时，考虑被操纵物体的共享动力学，来学习与其他智能体协作。当一个智能体与物体交互，导致特定的物体动力学变化时，其他智能体学习做出适当响应，从而实现队友之间的隐式通信与协调。与以往依赖基于跟踪方法的多角色人-物交互方法不同，CooHOI本质上是高效的，不依赖于多角色交互的运动捕捉数据，并且可以无缝扩展到包含更多参与者以及更广泛的物体类型。