Real-Time Generation of Near-Minimum-Energy Trajectories via Constraint-Informed Residual Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913653349941248 |
|---|---|
| author | Dona', Domenico Franzese, Giovanni Della Santina, Cosimo Boscariol, Paolo Lenzo, Basilio |
| author_facet | Dona', Domenico Franzese, Giovanni Della Santina, Cosimo Boscariol, Paolo Lenzo, Basilio |
| contents | Industrial robotics demands significant energy to operate, making energy-reduction methodologies increasingly important. Strategies for planning minimum-energy trajectories typically involve solving nonlinear optimal control problems (OCPs), which rarely cope with real-time requirements. In this paper, we propose a paradigm for generating near minimum-energy trajectories for manipulators by learning from optimal solutions. Our paradigm leverages a residual learning approach, which embeds boundary conditions while focusing on learning only the adjustments needed to steer a standard solution to an optimal one. Compared to a computationally expensive OCP-based planner, our paradigm achieves 87.3% of the performance near the training dataset and 50.8% far from the dataset, while being two to three orders of magnitude faster. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_09450 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Real-Time Generation of Near-Minimum-Energy Trajectories via Constraint-Informed Residual Learning Dona', Domenico Franzese, Giovanni Della Santina, Cosimo Boscariol, Paolo Lenzo, Basilio Robotics Industrial robotics demands significant energy to operate, making energy-reduction methodologies increasingly important. Strategies for planning minimum-energy trajectories typically involve solving nonlinear optimal control problems (OCPs), which rarely cope with real-time requirements. In this paper, we propose a paradigm for generating near minimum-energy trajectories for manipulators by learning from optimal solutions. Our paradigm leverages a residual learning approach, which embeds boundary conditions while focusing on learning only the adjustments needed to steer a standard solution to an optimal one. Compared to a computationally expensive OCP-based planner, our paradigm achieves 87.3% of the performance near the training dataset and 50.8% far from the dataset, while being two to three orders of magnitude faster. |
| title | Real-Time Generation of Near-Minimum-Energy Trajectories via Constraint-Informed Residual Learning |
| topic | Robotics |
| url | https://arxiv.org/abs/2501.09450 |