Task-Parameter Nexus: Task-Specific Parameter Learning for Model-Based Control
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917981366255616 |
|---|---|
| author | Cheng, Sheng Tao, Ran Gu, Yuliang Wang, Shenlong Wang, Xiaofeng Hovakimyan, Naira |
| author_facet | Cheng, Sheng Tao, Ran Gu, Yuliang Wang, Shenlong Wang, Xiaofeng Hovakimyan, Naira |
| contents | This paper presents the Task-Parameter Nexus (TPN), a learning-based approach for online determination of the (near-)optimal control parameters of model-based controllers (MBCs) for tracking tasks. In TPN, a deep neural network is introduced to predict the control parameters for any given tracking task at runtime, especially when optimal parameters for new tasks are not immediately available. To train this network, we constructed a trajectory bank with various speeds and curvatures that represent different motion characteristics. Then, for each trajectory in the bank, we auto-tune the optimal control parameters offline and use them as the corresponding ground truth. With this dataset, the TPN is trained by supervised learning. We evaluated the TPN on the quadrotor platform. In simulation experiments, it is shown that the TPN can predict near-optimal control parameters for a spectrum of tracking tasks, demonstrating its robust generalization capabilities to unseen tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_12448 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Task-Parameter Nexus: Task-Specific Parameter Learning for Model-Based Control Cheng, Sheng Tao, Ran Gu, Yuliang Wang, Shenlong Wang, Xiaofeng Hovakimyan, Naira Robotics Systems and Control This paper presents the Task-Parameter Nexus (TPN), a learning-based approach for online determination of the (near-)optimal control parameters of model-based controllers (MBCs) for tracking tasks. In TPN, a deep neural network is introduced to predict the control parameters for any given tracking task at runtime, especially when optimal parameters for new tasks are not immediately available. To train this network, we constructed a trajectory bank with various speeds and curvatures that represent different motion characteristics. Then, for each trajectory in the bank, we auto-tune the optimal control parameters offline and use them as the corresponding ground truth. With this dataset, the TPN is trained by supervised learning. We evaluated the TPN on the quadrotor platform. In simulation experiments, it is shown that the TPN can predict near-optimal control parameters for a spectrum of tracking tasks, demonstrating its robust generalization capabilities to unseen tasks. |
| title | Task-Parameter Nexus: Task-Specific Parameter Learning for Model-Based Control |
| topic | Robotics Systems and Control |
| url | https://arxiv.org/abs/2412.12448 |