发表机构
Technical University of Munich; Karlsruhe Institute of Technology; Shanghai Jiao Tong University（慕尼黑工业大学; 卡尔斯鲁厄理工学院; 上海交通大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究机器人操作模仿学习中如何保留任务几何形状与动态可允许运动，提出频谱运动基元框架，结合任务空间与关节空间调节，经实验验证该方法在多方面表现良好，能有效实现技能泛化。
AI 中文摘要
机器人操作的模仿学习应在生成动态可允许的机器人运动时保留已演示任务的几何形状。现有管道通常学习任务相关轨迹，之后通过滤波、平滑、裁剪或时间缩放施加执行限制，这可能扭曲关键任务的末端执行器路径。我们提出频谱运动基元（SMP），这是一种频域模仿学习框架，将任务空间技能生成与关节空间执行调节相结合。演示由截断的有限时域傅里叶系数表示。经验选择的低频任务带捕获主导运动几何形状，而高次谐波对导数增长贡献不成比例。基于帧感知的上下文条件GMM/GMR先验在规范任务帧中预测任务带系数，通过顺序逆运动学将生成的笛卡尔轨迹映射到关节空间。然后，相位耦合调节器在不修改频谱系数的情况下限制请求的相位进展，从而在保留表示路径的同时强制执行关节速度和加速度限制。实验评估了任务带重建、对复合演示损坏的鲁棒性、分布外跨板泛化、关节空间动态可允许性、末端执行器路径保留以及在Franka Panda机器人上的部署。结果显示出紧凑的几何重建、跨未见任务帧的一致转移、动态违规和急动的大幅减少以及在相位调节期间对预期末端执行器路径的保留。
英文摘要
Robot imitation learning for manipulation should preserve demonstrated task geometry while producing dynamically admissible robot motions. Existing pipelines often learn task-dependent trajectories and impose execution limits afterward through filtering, smoothing, clipping, or time scaling, which may distort task-critical end-effector paths. We propose the Spectral Movement Primitive (SMP), a frequency-domain imitation learning framework that couples task-space skill generation with joint-space execution regulation. Demonstrations are represented by truncated finite-horizon Fourier coefficients. An empirically selected low-frequency task band captures the dominant motion geometry, while higher harmonics contribute disproportionately to derivative growth. A frame-aware context-conditioned GMM/GMR prior predicts the task-band coefficients in a canonical task frame, and the resulting Cartesian trajectory is mapped to joint space through sequential inverse kinematics. A phase-coupled regulator then limits the requested phase progression without modifying the spectral coefficients, thereby enforcing joint velocity and acceleration limits while preserving the represented path. Experiments evaluate task-band reconstruction, robustness to composite demonstration corruption, out-of-distribution cross-board generalization, joint-space dynamic admissibility, end-effector path preservation, and deployment on a Franka Panda robot. Results show compact geometric reconstruction, consistent transfer across unseen task frames, substantial reductions in dynamic violations and jerk, and preservation of the intended end-effector path during phase regulation.
