Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.09462 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911582659805184 |
|---|---|
| author | Liu, Yu Yin, Yihang Huang, Tianlv Yan, Fei Xu, Yuan Hong, Weinan Han, Wei Cao, Yue Chen, Xiangyu Fan, Zipei Song, Xuan |
| author_facet | Liu, Yu Yin, Yihang Huang, Tianlv Yan, Fei Xu, Yuan Hong, Weinan Han, Wei Cao, Yue Chen, Xiangyu Fan, Zipei Song, Xuan |
| contents | Assistive teleoperation enhances efficiency via shared control, yet inter-operator variability, stemming from diverse habits and expertise, induces highly heterogeneous trajectory distributions that undermine intent recognition stability. We present Adaptor, a few-shot framework for robust cross-operator intent recognition. The Adaptor bridges the domain gap through two stages: (i) preprocessing, which models intent uncertainty by synthesizing trajectory perturbations via noise injection and performs geometry-aware keyframe extraction; and (ii) policy learning, which encodes the processed trajectories with an Intention Expert and fuses them with the pre-trained vision-language model context to condition an Action Expert for action generation. Experiments on real-world and simulated benchmarks demonstrate that Adaptor achieves state-of-the-art performance, improving success rates and efficiency over baselines. Moreover, the method exhibits low variance across operators with varying expertise, demonstrating robust cross-operator generalization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_09462 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Adaptor: Advancing Assistive Teleoperation with Few-Shot Learning and Cross-Operator Generalization Liu, Yu Yin, Yihang Huang, Tianlv Yan, Fei Xu, Yuan Hong, Weinan Han, Wei Cao, Yue Chen, Xiangyu Fan, Zipei Song, Xuan Robotics Assistive teleoperation enhances efficiency via shared control, yet inter-operator variability, stemming from diverse habits and expertise, induces highly heterogeneous trajectory distributions that undermine intent recognition stability. We present Adaptor, a few-shot framework for robust cross-operator intent recognition. The Adaptor bridges the domain gap through two stages: (i) preprocessing, which models intent uncertainty by synthesizing trajectory perturbations via noise injection and performs geometry-aware keyframe extraction; and (ii) policy learning, which encodes the processed trajectories with an Intention Expert and fuses them with the pre-trained vision-language model context to condition an Action Expert for action generation. Experiments on real-world and simulated benchmarks demonstrate that Adaptor achieves state-of-the-art performance, improving success rates and efficiency over baselines. Moreover, the method exhibits low variance across operators with varying expertise, demonstrating robust cross-operator generalization. |
| title | Adaptor: Advancing Assistive Teleoperation with Few-Shot Learning and Cross-Operator Generalization |
| topic | Robotics |
| url | https://arxiv.org/abs/2604.09462 |