Echo in the Steps: Learning Perceptive Humanoid Parkour with Gated Memory
cs.RO
Submitted: 2026-09-24
Updated: 2026-09-24
Project page: https://echo-in-the-steps.github.io
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Learning Humanoid Locomotion over Challenging Terrain
- Humanoid Locomotion and Manipulation: Current Progress and Challenges in Control, Planning, and Learning
- Gallant: Voxel Grid-based Humanoid Locomotion and Local-navigation across 3D Constrained Terrains
- Gait-Adaptive Perceptive Humanoid Locomotion with Real-Time Under-Base Terrain Reconstruction
- DPL: Depth-only Perceptive Humanoid Locomotion via Realistic Depth Synthesis and Cross-Attention Terrain Reconstruction
- BeamDojo: Learning Agile Humanoid Locomotion on Sparse Footholds
- Perceptive Humanoid Parkour: Chaining Dynamic Human Skills via Motion Matching
- Extreme Parkour with Legged Robots
- Learning Agile Locomotion on Risky Terrains
- Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model Learning
- MoE-Loco: Mixture of Experts for Multitask Locomotion
- Parkour in the Wild: Learning a General and Extensible Agile Locomotion Policy Using Multi-expert Distillation and RL Fine-tuning
- RPL: Learning Robust Humanoid Perceptive Locomotion on Challenging Terrains
- RMA: Rapid Motor Adaptation for Legged Robots
- ANYmal Parkour: Learning Agile Navigation for Quadrupedal Robots
- PIE: Parkour with Implicit-Explicit Learning Framework for Legged Robots
- START: Traversing Sparse Footholds with Terrain Reconstruction
- Coordinated Humanoid Robot Locomotion with Symmetry Equivariant Reinforcement Learning Policy
- Symmetry Considerations for Learning Task Symmetric Robot Policies
- Proximal Policy Optimization Algorithms
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