An integrated process for design and control of lunar robotics using AI and simulation
This addresses the problem of efficient lunar robotics development for space exploration, but it appears incremental as it builds on existing simulation and AI methods.
The paper tackles the challenge of developing lunar construction equipment by proposing an integrated process that explores physical design and control in parallel, using a technical framework based on OpenPLX language to link CAD models and autonomous systems to high-fidelity simulations, with case studies demonstrating capabilities such as an autonomous lunar rover combining vision-language models and reinforcement learning.
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.