DAWN: Noise-Robust Quadruped Parkour via Depth-Denoising World Models
cs.RO, cs.AI, cs.CV, cs.LG
Submitted: 2026-09-24
Updated: 2026-09-24
Comments: 8 pages, 6 figures. Accepted to IROS 2026
Project page: https://dawn-parkour.github.io
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Now You See That: Learning End-to-End Humanoid Locomotion from Raw Pixels
- DPL: Depth-only Perceptive Humanoid Locomotion via Realistic Depth Synthesis and Cross-Attention Terrain Reconstruction
- Learning Humanoid Locomotion with World Model Reconstruction
- Solving Rubik's Cube with a Robot Hand
- World Models
- Representation Learning with Contrastive Predictive Coding
- Contrastive Representation Learning for Robust Sim-to-Real Transfer of Adaptive Humanoid Locomotion
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
- Proximal Policy Optimization Algorithms
- The information bottleneck method
- Isaac Lab: A GPU-Accelerated Simulation Framework for Multi-Modal Robot Learning
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
- Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving