Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2312.14336 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913502610849792 |
|---|---|
| author | Briden, Julia Choi, Changrak Yun, Kyongsik Linares, Richard Cauligi, Abhishek |
| author_facet | Briden, Julia Choi, Changrak Yun, Kyongsik Linares, Richard Cauligi, Abhishek |
| contents | Future spacecraft and surface robotic missions require increasingly capable autonomy stacks for exploring challenging and unstructured domains, and trajectory optimization will be a cornerstone of such autonomy stacks. However, the nonlinear optimization solvers required remain too slow for use on relatively resource-constrained flight-grade computers. In this work, we turn towards amortized optimization, a learning-based technique for accelerating optimization run times, and present TOAST: Trajectory Optimization with Merit Function Warm Starts. Offline, using data collected from a simulation, we train a neural network to learn a mapping to the full primal and dual solutions given the problem parameters. Crucially, we build upon recent results from decision-focused learning and present a set of decision-focused loss functions using the notion of merit functions for optimization problems. We show that training networks with such constraint-informed losses can better encode the structure of the trajectory optimization problem and jointly learn to reconstruct the primal-dual solution while yielding improved constraint satisfaction. Through numerical experiments on a Lunar rover problem and a 3-degrees-of-freedom Mars powered descent guidance problem, we demonstrate that TOAST outperforms benchmark approaches in terms of both computation times and network prediction constraint satisfaction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_14336 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Constraint-Informed Learning for Warm Starting Trajectory Optimization Briden, Julia Choi, Changrak Yun, Kyongsik Linares, Richard Cauligi, Abhishek Robotics Future spacecraft and surface robotic missions require increasingly capable autonomy stacks for exploring challenging and unstructured domains, and trajectory optimization will be a cornerstone of such autonomy stacks. However, the nonlinear optimization solvers required remain too slow for use on relatively resource-constrained flight-grade computers. In this work, we turn towards amortized optimization, a learning-based technique for accelerating optimization run times, and present TOAST: Trajectory Optimization with Merit Function Warm Starts. Offline, using data collected from a simulation, we train a neural network to learn a mapping to the full primal and dual solutions given the problem parameters. Crucially, we build upon recent results from decision-focused learning and present a set of decision-focused loss functions using the notion of merit functions for optimization problems. We show that training networks with such constraint-informed losses can better encode the structure of the trajectory optimization problem and jointly learn to reconstruct the primal-dual solution while yielding improved constraint satisfaction. Through numerical experiments on a Lunar rover problem and a 3-degrees-of-freedom Mars powered descent guidance problem, we demonstrate that TOAST outperforms benchmark approaches in terms of both computation times and network prediction constraint satisfaction. |
| title | Constraint-Informed Learning for Warm Starting Trajectory Optimization |
| topic | Robotics |
| url | https://arxiv.org/abs/2312.14336 |