学习多任务机器人操作的语义原子技能
Learning Semantic Atomic Skills for Multi-Task Robotic Manipulation
AI总结：
提出AtomSkill框架，通过语义对比对齐和关键姿态想象，从演示中学习可重用原子技能，实现多任务机器人操作，优于现有方法。
摘要：
将模仿学习扩展到多样化的多任务机器人操作仍然具有挑战性，原因在于次优演示、行为多模态性和任务间的破坏性干扰。虽然基于技能的方法通过将行为分解为可重用的抽象提供了有希望的方向，但现有方法通常学习的技能要么偏向语言结构，要么缺乏跨任务的语义对齐，限制了泛化能力。在这项工作中，我们提出了AtomSkill，一种新颖的框架，从演示中学习语义对齐的原子技能空间，并通过关键姿态想象实现鲁棒的长时域执行。我们的方法引入了：(1) 语义对比技能对齐，将演示分割为可变长度的原子技能，并采用对比目标共同强制语义一致性和时间连贯性，产生紧凑且可重用的技能库；(2) 带关键姿态想象的动作解码，其中策略同时预测技能的终端关键姿态和即时动作，从而支持进度感知的技能转换。在推理过程中，原子技能扩散采样器生成合理的技能序列，而预测的关键姿态自动触发平滑的技能链。在仿真和真实世界环境中的大量实验表明，AtomSkill始终优于最先进的模仿学习和基于技能的基线。项目页面：此 https URL。
英文摘要：
Scaling imitation learning to diverse multi-task robot manipulation remains challenging due to suboptimal demonstrations, behavioral multi-modality, and destructive interference across tasks. While skill-based methods offer a promising direction by decomposing behaviors into reusable abstractions, existing approaches often learn skills that are either biased toward linguistic structure or lack semantic alignment across tasks, limiting generalization. In this work, we propose AtomSkill, a novel framework that learns a semantically aligned Atomic Skill Space from demonstrations and enables robust long-horizon execution through keypose imagination. Our method introduces: (1) semantic contrastive skill alignment, which partitions demonstrations into variable-length atomic skills and employs a contrastive objective to jointly enforce semantic consistency and temporal coherence, yielding a compact and reusable skill library; and (2) action decoding with keypose imagining, where the policy predicts both a skill's terminal keypose and immediate actions, thereby supporting progress-aware skill transitions. During inference, an atomic skill diffusion sampler generates plausible skill sequences, while predicted keyposes autonomously trigger smooth skill chaining. Extensive experiments in simulation and real-world settings show that AtomSkill consistently outperforms state-of-the-art imitation learning and skill-based baselines. Project page: https://atom-skill.github.io.
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。
