An integrated process for design and control of lunar robotics using AI and simulation
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_ | 1866918141555113984 |
|---|---|
| author | Lindmark, Daniel Andersson, Jonas Bodin, Kenneth Bodin, Tora Börjesson, Hugo Nordfeldth, Fredrik Servin, Martin |
| author_facet | Lindmark, Daniel Andersson, Jonas Bodin, Kenneth Bodin, Tora Börjesson, Hugo Nordfeldth, Fredrik Servin, Martin |
| contents | We envision an integrated process for developing lunar construction equipment, where physical design and control are explored in parallel. In this paper, we describe a technical framework that supports this process. It relies on OpenPLX, a readable/writable declarative language that links CAD-models and autonomous systems to high-fidelity, real-time 3D simulations of contacting multibody dynamics, machine regolith interaction forces, and non-ideal sensors. To demonstrate its capabilities, we present two case studies, including an autonomous lunar rover that combines a vision-language model for navigation with a reinforcement learning-based control policy for locomotion. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_12367 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | An integrated process for design and control of lunar robotics using AI and simulation Lindmark, Daniel Andersson, Jonas Bodin, Kenneth Bodin, Tora Börjesson, Hugo Nordfeldth, Fredrik Servin, Martin Robotics Artificial Intelligence We envision an integrated process for developing lunar construction equipment, where physical design and control are explored in parallel. In this paper, we describe a technical framework that supports this process. It relies on OpenPLX, a readable/writable declarative language that links CAD-models and autonomous systems to high-fidelity, real-time 3D simulations of contacting multibody dynamics, machine regolith interaction forces, and non-ideal sensors. To demonstrate its capabilities, we present two case studies, including an autonomous lunar rover that combines a vision-language model for navigation with a reinforcement learning-based control policy for locomotion. |
| title | An integrated process for design and control of lunar robotics using AI and simulation |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2509.12367 |