通过分解任务与组合技能，让机器人零样本完成复杂3D操作。
DeCo: Task Decomposition and Skill Composition for Zero-Shot Generalization in Long-Horizon 3D Manipulation
- 将操作演示拆解为可复用的原子动作模块，构建通用技能库。
- 在12个新任务上提升成功率66.67%~57.92%，真实场景零样本完成9项任务。
- 适合需要快速适应新指令的长时程机器人操作研究者使用。
将语言引导的多任务模仿学习模型推广到新颖的长时程3D操作任务极具挑战性。为此，我们提出DeCo（任务分解与技能组合）——一种模型无关框架，以增强对组合式长时程操作任务的零样本泛化能力。DeCo基于夹爪-物体交互，将模仿学习示范分解为模块化原子任务，构建可复用技能数据集。推理时，利用视觉-语言模型解析高层指令，检索相关技能并动态调度执行；空间感知的技能链模块确保动作间平滑无碰撞过渡。我们构建了DeCoBench基准，用于评估长时程操作中的组合泛化能力。DeCo使RVT-2、3DDA和ARP三个模仿学习模型在12个新任务上的成功率分别提升66.67%、21.53%和57.92%。在真实实验中，仅用6个原子任务训练的增强模型，零样本完成9个新任务，成功率比基线提升53.33%。
原文摘要 · Abstract (English)
Generalizing language-conditioned multi-task imitation learning (IL) models to novel long-horizon 3D manipulation tasks is challenging. To address this, we propose DeCo (Task Decomposition and Skill Composition), a model-agnostic framework that enhances zero-shot generalization to compositional long-horizon manipulation tasks. DeCo decomposes IL demonstrations into modular atomic tasks based on gripper-object interactions, creating a dataset that enables models to learn reusable skills. At inference, DeCo uses a vision-language model (VLM) to parse high-level instructions, retrieve relevant skills, and dynamically schedule their execution. A spatially-aware skill-chaining module ensures smooth, collision-free transitions between skills. We introduce DeCoBench, a benchmark designed to evaluate compositional generalization in long-horizon manipulation tasks. DeCo improves the success rate of three IL models, RVT-2, 3DDA, and ARP, by 66.67%, 21.53%, and 57.92%, respectively, on 12 novel tasks. In real-world experiments, the DeCo-enhanced model, trained on only 6 atomic tasks, completes 9 novel tasks in zero-shot, with a 53.33% improvement over the baseline model. Project website: https://deco226.github.io.
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。