用空间引导让机器人学会拼乐高式积木，能举一反三。
BrickCraft: Visuomotor Skill Composition with Situated Manual Guidance for Long-Horizon Interlocking Brick Assembly
- 以参考积木为基准，把复杂拼装拆成可复用的基本动作。
- 仅需少量示范就能掌握技能，对新结构也能有效拼装。
- 适合做长时序、需空间理解的机器人操作任务研究者。
自主机器人完成互锁积木的拼装，需要无缝融合长时序任务推理、空间定位和精细操控。本文提出 BrickCraft，一种用于长时序且可泛化的互锁积木拼装组合框架。BrickCraft 采用相对表述方式建模拼装过程，每一步以部分结构中的参考积木为锚点，从而将复杂任务分解为有限的一组可复用基本技能。通过情境化操作手册，BrickCraft 将高层拼装计划与物理执行衔接，将拼装意图投影到实时机器人观测中，为学习到的视觉-运动技能提供明确的空间引导。最后，BrickCraft 采用组合式执行流程，串联这些空间锚定技能来完成长时序拼装任务。大量实验验证表明，BrickCraft 能从有限示范中习得熟练拼装技能，并对未见结构展现出强组合泛化能力。
原文摘要 · Abstract (English)
Autonomous robotic assembly of interlocking bricks demands seamless integration of long-horizon task reasoning, spatial grounding, and fine-grained manipulation. This paper presents BrickCraft, a compositional framework designed for long-horizon and generalizable interlocking brick assembly. BrickCraft models the assembly process using a relative formulation, where each step is anchored to a reference brick within the partial structure, thereby decomposing complex tasks into a finite set of reusable primitive skills. BrickCraft bridges the gap between high-level assembly plans and physical execution through situated manuals, which provide explicit spatial guidance for learned visuomotor skills by projecting the assembly intent onto real-time robot observations. Finally, BrickCraft employs a compositional execution pipeline that chains these spatially grounded skills to accomplish long-horizon assembly tasks. Extensive experimental validations demonstrate that BrickCraft acquires proficient assembly skills from a limited set of demonstrations and exhibits strong compositional generalization to unseen structures. The project website is available at https://intelligent-control-lab.github.io/BrickCraft.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。