KITE：解耦运动学和交互以实现零样本跨实体操作
KITE: Decoupling Kinematics and Interaction for Zero-Shot Cross-Embodiment Manipulation
AI总结：
提出KITE框架，通过解耦任务推理与实体特定运动控制，利用接触模式学习交互意图的潜在表示，实现零样本跨实体操作迁移。
摘要：
跨机器人实体泛化操作策略仍然困难，因为标准策略将任务推理与实体特定的运动控制纠缠在一起。我们研究零样本跨实体操作，其中在源实体上训练的策略必须部署在结构不同的目标实体上，无需额外的任务演示。我们引入跨实体的运动学交互迁移（KITE），它将操作解耦为与实体无关的任务推理和实体特定的运动控制，通过基于接触模式的学习到的交互意图潜在表示连接。任务推理由共享策略执行，该策略从源演示中预测潜在意图，而运动控制由从每个实体的运动学模型学习到的意图条件动作解码器执行。使用KITE，适应新实体仅需使用其运动学模型训练新的动作解码器，无需重新收集演示数据。我们在三个操作任务上评估KITE，涵盖平行夹爪、灵巧手和复合实体之间的迁移。KITE一致地实现了对结构不同目标实体的零样本迁移，在迁移成功率和任务-实体范围方面优于最先进的基线方法。
英文摘要：
Generalizing manipulation policies across robot embodiments remains difficult because standard policies entangle task reasoning with embodiment-specific motor control. We study zero-shot cross-embodiment manipulation, where a policy trained on source embodiments must be deployed on a structurally different target embodiment without additional task demonstrations. We introduce Kinematic Interaction Transfer across Embodiments (KITE), which decouples manipulation into embodiment-agnostic task reasoning and embodiment-specific motor control, connected through a learned latent representation of interaction intent based on contact patterns. Task reasoning is performed by a shared policy that predicts latent intents from source demonstrations, while motor control is performed by an intent-conditioned action decoder learned from each embodiment's kinematic model. With KITE, adaptation to a new embodiment requires only training a new action decoder using its kinematic model, without recollecting demonstration data. We evaluate KITE on three manipulation tasks spanning transfer between parallel grippers, dexterous hands, and composite embodiments. KITE consistently achieves zero-shot transfer to structurally different target embodiments, outperforming state-of-the-art baselines in transfer success and task-embodiment scope.
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。
