Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.19853 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908556603686912 |
|---|---|
| author | Wu, BinXu Zhang, TengFei Yang, Chen Wen, JiaHao Li, HaoCheng Ma, JingTian Chen, Zhen Wang, JingYuan |
| author_facet | Wu, BinXu Zhang, TengFei Yang, Chen Wen, JiaHao Li, HaoCheng Ma, JingTian Chen, Zhen Wang, JingYuan |
| contents | Multi-stage sequential (MSS) robotic manipulation tasks are prevalent and crucial in robotics. They often involve state ambiguity, where visually similar observations correspond to different actions. We present SAGE, a state-aware guided imitation learning framework that models tasks as a Hidden Markov Decision Process (HMDP) to explicitly capture latent task stages and resolve ambiguity. We instantiate the HMDP with a state transition network that infers hidden states, and a state-aware action policy that conditions on both observations and hidden states to produce actions, thereby enabling disambiguation across task stages. To reduce manual annotation effort, we propose a semi-automatic labeling pipeline combining active learning and soft label interpolation. In real-world experiments across multiple complex MSS tasks with state ambiguity, SAGE achieved 100% task success under the standard evaluation protocol, markedly surpassing the baselines. Ablation studies further show that such performance can be maintained with manual labeling for only about 13% of the states, indicating its strong effectiveness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_19853 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SAGE:State-Aware Guided End-to-End Policy for Multi-Stage Sequential Tasks via Hidden Markov Decision Process Wu, BinXu Zhang, TengFei Yang, Chen Wen, JiaHao Li, HaoCheng Ma, JingTian Chen, Zhen Wang, JingYuan Robotics Multi-stage sequential (MSS) robotic manipulation tasks are prevalent and crucial in robotics. They often involve state ambiguity, where visually similar observations correspond to different actions. We present SAGE, a state-aware guided imitation learning framework that models tasks as a Hidden Markov Decision Process (HMDP) to explicitly capture latent task stages and resolve ambiguity. We instantiate the HMDP with a state transition network that infers hidden states, and a state-aware action policy that conditions on both observations and hidden states to produce actions, thereby enabling disambiguation across task stages. To reduce manual annotation effort, we propose a semi-automatic labeling pipeline combining active learning and soft label interpolation. In real-world experiments across multiple complex MSS tasks with state ambiguity, SAGE achieved 100% task success under the standard evaluation protocol, markedly surpassing the baselines. Ablation studies further show that such performance can be maintained with manual labeling for only about 13% of the states, indicating its strong effectiveness. |
| title | SAGE:State-Aware Guided End-to-End Policy for Multi-Stage Sequential Tasks via Hidden Markov Decision Process |
| topic | Robotics |
| url | https://arxiv.org/abs/2509.19853 |