IntentVLA: Short-Horizon Intent Modeling for Aliased Robot Manipulation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913128964423680 |
|---|---|
| author | Lian, Shijie Yu, Bin Lin, Xiaopeng Shen, Zhaolong Yang, Laurence Tianruo Jin, Yurun Liu, Haishan Wu, Changti Yuan, Hang Huang, Cong Chen, Kai |
| author_facet | Lian, Shijie Yu, Bin Lin, Xiaopeng Shen, Zhaolong Yang, Laurence Tianruo Jin, Yurun Liu, Haishan Wu, Changti Yuan, Hang Huang, Cong Chen, Kai |
| contents | Robot imitation data are often multimodal: similar visual-language observations may be followed by different action chunks because human demonstrators act with different short-horizon intents, task phases, or recent context. Existing frame-conditioned VLA policies infer each chunk from the current observation and instruction alone, so under partial observability they may resample different intents across adjacent replanning steps, leading to inter-chunk conflict and unstable execution. We introduce IntentVLA, a history-conditioned VLA framework that encodes recent visual observations into a compact short-horizon intent representation and uses it to condition chunk generation. We further introduce AliasBench, a 12-task ambiguity-aware benchmark on RoboTwin2 with matched training data and evaluation environments that isolate short-horizon observation aliasing. Across AliasBench, SimplerEnv, LIBERO, and RoboCasa, IntentVLA improves rollout stability and outperforms strong VLA baselines |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_14712 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | IntentVLA: Short-Horizon Intent Modeling for Aliased Robot Manipulation Lian, Shijie Yu, Bin Lin, Xiaopeng Shen, Zhaolong Yang, Laurence Tianruo Jin, Yurun Liu, Haishan Wu, Changti Yuan, Hang Huang, Cong Chen, Kai Robotics Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition Robot imitation data are often multimodal: similar visual-language observations may be followed by different action chunks because human demonstrators act with different short-horizon intents, task phases, or recent context. Existing frame-conditioned VLA policies infer each chunk from the current observation and instruction alone, so under partial observability they may resample different intents across adjacent replanning steps, leading to inter-chunk conflict and unstable execution. We introduce IntentVLA, a history-conditioned VLA framework that encodes recent visual observations into a compact short-horizon intent representation and uses it to condition chunk generation. We further introduce AliasBench, a 12-task ambiguity-aware benchmark on RoboTwin2 with matched training data and evaluation environments that isolate short-horizon observation aliasing. Across AliasBench, SimplerEnv, LIBERO, and RoboCasa, IntentVLA improves rollout stability and outperforms strong VLA baselines |
| title | IntentVLA: Short-Horizon Intent Modeling for Aliased Robot Manipulation |
| topic | Robotics Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.14712 |