Terrain Traversal Without Motion Priors: Expert-Routed Humanoid Locomotion at Deployment Fidelity
cs.RO
Submitted: 2026-10-07
Updated: 2026-10-07
Comments: https://fai-rl-tech.github.io/moe-perceptive/
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Learning Whole-Body Humanoid Locomotion via Motion Generation and Motion Tracking
- T-GMP: Terrain-conditioned Generative Motion Priors for Versatile and Natural Humanoid Locomotion
- CMoE: Contrastive Mixture of Experts for Motion Control and Terrain Adaptation of Humanoid Robots
- TAGA: Terrain-aware Active Gaze Learning for Generalizable Agile Humanoid Locomotion
- CoRe-MoE: Contrastive Reweighted Mixture of Experts for Multi-Terrain Humanoid Locomotion with Gait Adaptation
- CTS-MoE: Implicit Terrain Adaptation via Mixture-of-Experts for Perceptive Locomotion
- Mixture-of-Experts RL for Fault-Tolerant Legged Locomotion
- Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
- Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
- Representation Learning with Contrastive Predictive Coding
- Legged Locomotion in Challenging Terrains using Egocentric Vision
- Learning Humanoid Locomotion over Challenging Terrain
- Learning Humanoid Locomotion with Perceptive Internal Model
- Gallant: Voxel Grid-based Humanoid Locomotion and Local-navigation across 3D Constrained Terrains
- Now You See That: Learning End-to-End Humanoid Locomotion from Raw Pixels
- CReF: Cross-modal and Recurrent Fusion for Depth-conditioned Humanoid Locomotion
- DPL: Depth-only Perceptive Humanoid Locomotion via Realistic Depth Synthesis and Cross-Attention Terrain Reconstruction
- Perceptive Variable-Timing Footstep Planning for Humanoid Locomotion on Disconnected Footholds
- Learning a Vision-Based Footstep Planner for Hierarchical Walking Control
- FastStair: Learning to Run Up Stairs with Humanoid Robots
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
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies