Generalizable Multistage Assembly via One-Shot Category-Level Demonstration
- 4 November 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 37 (3) , 1149-1162
Abstract
Imitation learning offers a flexible approach for robot skill acquisition, enabling robots to learn complex tasks directly from demonstrations. However, most existing methods require a large number of demonstrations, whereas humans typically only need one or a few demonstrations. This discrepancy results in significant time consumption for data collection. Furthermore, these methods often assume that test scenarios will always be identical to the demonstration, which can lead to substantial performance degradation when facing novel scenarios, such as manipulating objects from the same category but with different shapes and sizes, or encountering object collisions during manipulation. To address these challenges, we propose a generalized multistage manipulation network for category-level robot assembly tasks. This network allows a robot to learn a multistage screw–nut assembly task from a single demonstration and generalize to new object instances with varying shapes and sizes. Specifically, the network uses category-level pose estimation to extract manipulation trajectories from the demonstration and applies manipulation-pose generalization to transfer these trajectories to novel instances. In addition, real-time action correction adjusts the trajectory based on real-time force feedback, enabling the robot to adapt to unexpected collisions during execution. We validate our method through experiments in both simulation and real-world environments, verifying its effectiveness and flexibility.Keywords
Funding Information
- National Key Research and Development Program of China (2023YFB4704800)
- National Natural Science Foundation of China (62225310)
- National Natural Science Foundation of China (62003336)
- Fundamental Research Funds for the Central Universities
This publication has 44 references indexed in Scilit:
- Learning force-conditioned visuomotor diffusion policy from human demonstrations for complex robotic assembly tasksManufacturing Letters, 2025
- GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Parts2023
- CAMS: CAnonicalized Manipulation Spaces for Category-Level Functional Hand-Object Manipulation Synthesis2023
- Shape-Pose Disentanglement Using SE(3)-Equivariant Vector Neurons2022
- U2-Net: Going deeper with nested U-structure for salient object detectionPattern Recognition, 2020
- Category-Level Articulated Object Pose Estimation2020
- Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation2019
- Occupancy Networks: Learning 3D Reconstruction in Function Space2019
- 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation2016
- Fast Global Registration2016