BrickCraft-Duo：面向组合式长时程装配的高效双臂技能学习与精化

中文摘要 AI 辅助

互锁砖块装配为评估真实世界机器人操作能力提供了一个代表性测试平台，其中多样化的结构设计、复杂的步骤间依赖、错综复杂的机械交互以及紧密的插入公差构成了重大挑战。我们提出了BrickCraft-Duo，一个模块化框架，通过数据高效的技能学习与组合，实现互锁砖块的长时程双臂协作装配。BrickCraft-Duo从多样化的演示中学习可复用的单臂和双臂装配技能，通过双侧对称对齐促进对称手臂之间的技能共享以及装配-支撑角色分配。在稳定性感知的装配推理引导下，BrickCraft-Duo组合异构技能以实现自主的长时程执行，并进一步集成人在回路的纠正以进行针对性的技能精化。所得到的系统在涉及部分支撑配置的五项真实世界装配任务中，实现了至少60%的长时程成功率和至少95%的步骤级完成率，任务时间跨度长达九个步骤。项目网站：https://jichuan-yu.github.io/BrickCraft-Duo。

英文摘要

Interlocking brick assembly provides a representative testbed for evaluating real-world robotic manipulation capabilities, where diverse structural designs, complex inter-step dependencies, intricate mechanical interactions and tight insertion tolerances pose substantial challenges. We present BrickCraft-Duo, a modular framework for long-horizon dual-arm collaborative assembly of interlocking bricks through data-efficient skill learning and composition. BrickCraft-Duo learns reusable single- and dual-arm assembly skills from diverse demonstrations, with bilateral symmetry alignment facilitating skill sharing across symmetric arms and assembly--support role assignments. Guided by stability-aware assembly reasoning, BrickCraft-Duo composes heterogeneous skills to achieve autonomous long-horizon execution, and further integrates human-in-the-loop correction for targeted skill refinement. The resulting system achieves long-horizon success rates of at least 60% and step-level completion rates of at least 95% across five real-world assembly tasks involving partially supported configurations, with horizons of up to nine steps. Project website: https://jichuan-yu.github.io/BrickCraft-Duo.

发表机构

• Tsinghua University（清华大学）
• Carnegie Mellon University（卡内基梅隆大学）

机构由 AI 辅助整理，请以论文原文为准。