Event
Light-Aware Planning Framework Improves Spacecraft Inspection Imaging
1 reports · 1 sources
Sagarika Rao Valluri and Benjamin Riviere propose a light-aware active perception planning framework for spacecraft inspection, replacing geometric visibility checks with a learned camera information metric based on a classification variational autoencoder (VAE) to address inspection failures caused by drastic orbital lighting variations. The authors state that the method implements a guidance, navigation, and control architecture in a realistic physics simulator and tests multiple orbital lighting conditions and viewpoints: average brightness reaches 0.57, with 81.6% of observations above 0.25; by contrast, geometric planning with a lighting band is 0.02 (3.0%), and pure geometric planning is 0.04 (6.0%). These results come from a simulated environment and have not yet been validated on a real spacecraft.
Report timeline
- Illumination-aware active perception for spacecraft inspection
The authors propose an inspection planning framework that replaces geometric visibility checks with a learned camera information metric based on a classifier variational autoencoder (VAE), to address inspection failures caused by drastic orbital illumination changes. The method implements a guidance, navigation, and control architecture in a photorealistic physics simulator and tests multiple orbital illumination conditions and viewpoints: average brightness reaches 0.57, with 81.6% of observations above 0.25, compared with 0.02 (3.0%) for geometric planning with illumination bands and 0.04 (6.0%) for pure geometric planning.
arXiv cs.RO ·