P-BFM: Perceptive Behavioral Foundation Models for Humanoid Control via Unsupervised Reinforcement Learning
cs.RO
Submitted: 2026-10-11
Updated: 2026-10-11
Comments: Project page: https://roboparty.github.io/P-BFM/
Project page: https://roboparty.github.io/P-BFM
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- PILOT: A Perceptive Integrated Low-level Controller for Loco-manipulation over Unstructured Scenes
- Learning Vision-Based Bipedal Locomotion for Challenging Terrain
- Attention-Based Map Encoding for Learning Generalized Legged Locomotion
- BFM-Zero: A Promptable Behavioral Foundation Model for Humanoid Control Using Unsupervised Reinforcement Learning
- BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion
- Learning Humanoid Locomotion with Perceptive Internal Model
- Gait-Adaptive Perceptive Humanoid Locomotion with Real-Time Under-Base Terrain Reconstruction
- Now You See That: Learning End-to-End Humanoid Locomotion from Raw Pixels
- Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Models
- MoRE: Mixture of Residual Experts for Humanoid Lifelike Gaits Learning on Complex Terrains
- Perceptive Behavior Foundation Model: Adapting Human Motion Priors to Robot-Centric Terrain
- Perceptive Humanoid Parkour: Chaining Dynamic Human Skills via Motion Matching
- Humanoid Parkour Learning
- Deep Whole-body Parkour
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