ROCVFeb 17, 2025

FUNCTO: Function-Centric One-Shot Imitation Learning for Tool Manipulation

arXiv:2502.11744v212 citationsh-index: 7
Originality Incremental advance
AI Analysis

This addresses a key limitation in one-shot imitation learning for robotics, allowing more intuitive and efficient teaching of tool use, though it appears incremental as it builds on existing OSIL frameworks.

The paper tackles the problem of enabling robots to generalize tool manipulation skills from a single human demonstration to novel tools with the same function despite geometric variations, achieving superior performance in real-robot experiments compared to existing methods.

Learning tool use from a single human demonstration video offers a highly intuitive and efficient approach to robot teaching. While humans can effortlessly generalize a demonstrated tool manipulation skill to diverse tools that support the same function (e.g., pouring with a mug versus a teapot), current one-shot imitation learning (OSIL) methods struggle to achieve this. A key challenge lies in establishing functional correspondences between demonstration and test tools, considering significant geometric variations among tools with the same function (i.e., intra-function variations). To address this challenge, we propose FUNCTO (Function-Centric OSIL for Tool Manipulation), an OSIL method that establishes function-centric correspondences with a 3D functional keypoint representation, enabling robots to generalize tool manipulation skills from a single human demonstration video to novel tools with the same function despite significant intra-function variations. With this formulation, we factorize FUNCTO into three stages: (1) functional keypoint extraction, (2) function-centric correspondence establishment, and (3) functional keypoint-based action planning. We evaluate FUNCTO against exiting modular OSIL methods and end-to-end behavioral cloning methods through real-robot experiments on diverse tool manipulation tasks. The results demonstrate the superiority of FUNCTO when generalizing to novel tools with intra-function geometric variations. More details are available at https://sites.google.com/view/functo.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes