DAWN: Noise-Robust Quadruped Parkour via Depth-Denoising World Models
DAWN is a noise-robust perception framework for legged locomotion which builds noise robustness directly into a world model via two modifications: feeding noisy depth to the encoder while keeping clean depth as the reconstruction target, forcing the model to implicitly denoise its input.
Yo-Han Choi, Min-Jun Kim, Jin-Sung Kim et al.
· 1 citation