Active Constraint Learning in High Dimensions from Demonstrations
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917172380434432 |
|---|---|
| author | Qiu, Zheng Chiu, Chih-Yuan Chou, Glen |
| author_facet | Qiu, Zheng Chiu, Chih-Yuan Chou, Glen |
| contents | We present an iterative active constraint learning (ACL) algorithm, within the learning from demonstrations (LfD) paradigm, which intelligently solicits informative demonstration trajectories for inferring an unknown constraint in the demonstrator's environment. Our approach iteratively trains a Gaussian process (GP) on the available demonstration dataset to represent the unknown constraints, uses the resulting GP posterior to query start/goal states, and generates informative demonstrations which are added to the dataset. Across simulation and hardware experiments using high-dimensional nonlinear dynamics and unknown nonlinear constraints, our method outperforms a baseline, random-sampling based method at accurately performing constraint inference from an iteratively generated set of sparse but informative demonstrations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_22757 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Active Constraint Learning in High Dimensions from Demonstrations Qiu, Zheng Chiu, Chih-Yuan Chou, Glen Robotics Artificial Intelligence Machine Learning Systems and Control Optimization and Control We present an iterative active constraint learning (ACL) algorithm, within the learning from demonstrations (LfD) paradigm, which intelligently solicits informative demonstration trajectories for inferring an unknown constraint in the demonstrator's environment. Our approach iteratively trains a Gaussian process (GP) on the available demonstration dataset to represent the unknown constraints, uses the resulting GP posterior to query start/goal states, and generates informative demonstrations which are added to the dataset. Across simulation and hardware experiments using high-dimensional nonlinear dynamics and unknown nonlinear constraints, our method outperforms a baseline, random-sampling based method at accurately performing constraint inference from an iteratively generated set of sparse but informative demonstrations. |
| title | Active Constraint Learning in High Dimensions from Demonstrations |
| topic | Robotics Artificial Intelligence Machine Learning Systems and Control Optimization and Control |
| url | https://arxiv.org/abs/2512.22757 |