Developing intelligent robots for complex manipulation tasks in household and factory settings remains challenging due to long-horizon tasks, contact-rich manipulation, and the need to generalize across a wide variety of object shapes and scene layouts. While Task and Motion Planning (TAMP) offers a promising solution, its assumptions such as kinodynamic models limit applicability in novel contexts. Neural object descriptors (NODs) have shown promise in object and scene generalization but face limitations in addressing broader tasks. Our proposed TAMP-based framework, NOD-TAMP, extracts short manipulation trajectories from a handful of human demonstrations, adapts these trajectories using NOD features, and composes them to solve broad long-horizon tasks. Validated in a simulation environment, NOD-TAMP effectively tackles varied challenges and outperforms existing methods, establishing a cohesive framework for manipulation planning. For videos and other supplemental material, see the project website: https://sites.google.com/view/nod-tamp/.

翻译：[translated abstract in Chinese] 开发用于家庭和工厂环境中复杂操作任务的智能机器人仍面临挑战，原因在于任务周期长、操作过程接触密集，且需要泛化到各种物体形状和场景布局。尽管任务与运动规划（TAMP）提供了有前景的解决方案，但其对运动动力学模型等假设限制了在新场景中的应用。神经对象描述符（NOD）在物体与场景泛化方面展现出潜力，但在处理更广泛任务时存在局限。我们提出的基于TAMP的框架NOD-TAMP，从少量人类演示中提取短操作轨迹，利用NOD特征适配这些轨迹，并将其组合以解决广泛的长周期任务。在模拟环境中的验证表明，NOD-TAMP能有效应对各类挑战，且性能优于现有方法，为操作规划建立了统一的框架。相关视频及补充材料请参见项目网站：https://sites.google.com/view/nod-tamp/。