Physics-Guided Residual Reinforcement Learning for Humanoid Narrow-Path Traversal

arXiv:2508.20661 · cs.RO · Submitted 2025-08-28 · Read on arXiv

cs.RO

Submitted: 2025-08-28

Updated: 2026-09-24

Comments: Project website: https://huangtc233.github.io/Traversing-the-Narrow-Path/

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Reinforcement Learning — 14× in this paper · explained in 4 episodes
• Ablation — 7× in this paper · explained in 1 episode
• Ablation study — 6× in this paper · explained in 3 episodes
• Interpretability — 5× in this paper · explained in 15 episodes
• Reward Function — 4× in this paper · explained in 4 episodes
• Adaptation — 3× in this paper · explained in 1 episode
• Alternation — 3× in this paper
• Regularization — 3× in this paper · explained in 3 episodes
• Two-stage training — 3× in this paper · explained in 2 episodes
• Action Space — 2× in this paper · explained in 1 episode
• Center of Mass — 2× in this paper
• Generalization — 2× in this paper · explained in 13 episodes
• Instantaneous Capture Point — 2× in this paper
• Robustness — 2× in this paper · explained in 5 episodes
• Sim-to-Real Transfer — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper
• Center of Mass (CoM) — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Online Adaptation — 1× in this paper · explained in 3 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes

Sources

• BeamDojo: Learning Agile Humanoid Locomotion on Sparse Footholds
• Integrating Model-Based Footstep Planning with Model-Free Reinforcement Learning for Dynamic Legged Locomotion
• Orientation-Aware Model Predictive Control with Footstep Adaptation for Dynamic Humanoid Walking
• Bipedal Walking on Constrained Footholds: Momentum Regulation via Vertical COM Control
• Adaptive Step Duration for Accurate Foot Placement: Achieving Robust Bipedal Locomotion on Terrains with Restricted Footholds
• Residual Policy Learning
• ALLSTEPS: Curriculum-driven Learning of Stepping Stone Skills
• Elevation Mapping for Locomotion and Navigation using GPU

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