TAGA: Terrain-aware Active Gaze Learning for Generalizable Agile Humanoid Locomotion
cs.RO
Submitted: 2026-06-04
Updated: 2026-09-24
Project page: https://marmotlab.github.io/taga-humanoid
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- HOMIE: Humanoid Loco-Manipulation with Isomorphic Exoskeleton Cockpit
- FALCON: Learning Force-Adaptive Humanoid Loco-Manipulation
- Bridging the Sim-to-Real Gap for Athletic Loco-Manipulation
- HumanPlus: Humanoid Shadowing and Imitation from Humans
- AME-2: Agile and Generalized Legged Locomotion via Attention-Based Neural Map Encoding
- BeamDojo: Learning Agile Humanoid Locomotion on Sparse Footholds
- Parkour in the Wild: Learning a General and Extensible Agile Locomotion Policy Using Multi-expert Distillation and RL Fine-tuning
- DPL: Depth-only Perceptive Humanoid Locomotion via Realistic Depth Synthesis and Cross-Attention Terrain Reconstruction
- Gallant: Voxel Grid-based Humanoid Locomotion and Local-navigation across 3D Constrained Terrains
- KiVi: Kinesthetic-Visuospatial Integration for Dynamic and Safe Egocentric Legged Locomotion
- ADAPT: Adaptive Dual-projection Architecture for Perceptive Traversal
- CART: Context-Aware Terrain Adaptation using Temporal Sequence Selection for Legged Robots
- CMoE: Contrastive Mixture of Experts for Motion Control and Terrain Adaptation of Humanoid Robots
- RSL-RL: A Learning Library for Robotics Research
- Isaac Lab: A GPU-Accelerated Simulation Framework for Multi-Modal Robot Learning
- CReF: Cross-modal and Recurrent Fusion for Depth-conditioned Humanoid Locomotion
- Now You See That: Learning End-to-End Humanoid Locomotion from Raw Pixels
- MoRE: Mixture of Residual Experts for Humanoid Lifelike Gaits Learning on Complex Terrains
- Hiking in the Wild: A Scalable Perceptive Parkour Framework for Humanoids
- RPL: Learning Robust Humanoid Perceptive Locomotion on Challenging Terrains
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