PoCo：源自并服务于异构机器人学习的策略组合
PoCo: Policy Composition from and for Heterogeneous Robot Learning
AI总结：
本文提出 PoCo 策略组合方法，用扩散模型表示并融合跨模态、跨领域异构机器人数据，实现多任务泛化操作与推理时行为调整，在工具使用任务中优于单一数据源基线。
摘要：
从面向不同任务的异构数据中训练通用机器人策略是一项重大挑战。现有机器人数据集在颜色、深度、触觉和本体感受信息等模态上存在差异，并且采集自仿真、真实机器人和人类视频等不同领域。当前方法通常收集并汇集来自一个领域的所有数据，以训练单一策略来处理任务和领域中的这种异构性，而这成本高昂且实施困难。在本工作中，我们提出一种称为 Policy Composition（策略组合）的灵活方法，通过组合以扩散模型表示的不同数据分布，跨此类多样模态和领域融合信息，以学习场景级和任务级的泛化操作技能。我们的方法可利用任务级组合实现多任务操作，并可与解析代价函数组合，在推理时调整策略行为。我们在仿真、人类和真实机器人数据上训练该方法，并在工具使用任务中进行评估。经组合的策略在变化的场景和任务下取得稳健且灵巧的性能，并在仿真和真实世界实验中均优于来自单一数据源的基线方法。更多细节见 https://liruiw.github.io/policycomp。
英文摘要：
Training general robotic policies from heterogeneous data for different tasks is a significant challenge. Existing robotic datasets vary in different modalities such as color, depth, tactile, and proprioceptive information, and collected in different domains such as simulation, real robots, and human videos. Current methods usually collect and pool all data from one domain to train a single policy to handle such heterogeneity in tasks and domains, which is prohibitively expensive and difficult. In this work, we present a flexible approach, dubbed Policy Composition, to combine information across such diverse modalities and domains for learning scene-level and task-level generalized manipulation skills, by composing different data distributions represented with diffusion models. Our method can use task-level composition for multi-task manipulation and be composed with analytic cost functions to adapt policy behaviors at inference time. We train our method on simulation, human, and real robot data and evaluate in tool-use tasks. The composed policy achieves robust and dexterous performance under varying scenes and tasks and outperforms baselines from a single data source in both simulation and real-world experiments. See https://liruiw.github.io/policycomp for more details .
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
