超越预定义动作：整合行为树与动态运动基元以实现机器人从演示中学习
Beyond Predefined Actions: Integrating Behavior Trees and Dynamic Movement Primitives for Robot Learning from Demonstration
AI总结：
提出将 DMP 控制器集成进 BT 框架的方法，从单次演示联合学习任务结构与运动动作，消除预定义动作需求并提升策略可解释性、模块化与适应性。
摘要：
诸如 Behavior Trees（BT，行为树）和 Dynamic Motion Primitives（DMP，动态运动基元）等可解释策略表示，使机器人能够从人类演示中迁移技能，但二者各有局限：BT 需要专家精心设计的低层动作，而 DMP 缺乏高层任务逻辑。我们通过将 DMP 控制器集成到 BT 框架中来解决这些局限，从单次演示中联合学习 BT 结构与 DMP 动作，从而不再需要预定义动作。此外，通过将 BT 决策逻辑与 DMP 运动生成相结合，我们的方法增强了自主系统策略的可解释性、模块化和适应性。该方法既可学习复现低层运动，也能将局部演示组合成连贯且易于修改的整体策略。
英文摘要：
Interpretable policy representations like Behavior Trees (BTs) and Dynamic Motion Primitives (DMPs) enable robot skill transfer from human demonstrations, but each faces limitations: BTs require expert-crafted low-level actions, while DMPs lack high-level task logic. We address these limitations by integrating DMP controllers into a BT framework, jointly learning the BT structure and DMP actions from single demonstrations, thereby removing the need for predefined actions. Additionally, by combining BT decision logic with DMP motion generation, our method enhances policy interpretability, modularity, and adaptability for autonomous systems. Our approach readily affords both learning to replicate low-level motions and combining partial demonstrations into a coherent and easy-to-modify overall policy.
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。
