Humanoid Horizon: Extending Task Horizon in Whole-Body Loco-Manipulation via Parallel Training, Dynamic Starting, and Reward Gating
cs.RO, cs.GR
Submitted: 2026-10-06
Updated: 2026-10-06
Comments: Videos and results are available at https://haozhuo-zhang.github.io/Humanoid-Horizon-project-page/
Project page: https://haozhuo-zhang.github.io/Humanoid-Horizon-project-page
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Unified Human-Scene Interaction via Prompted Chain-of-Contacts
- PhysHOI: Physics-Based Imitation of Dynamic Human-Object Interaction
- Humanoid-VLA: Towards Universal Humanoid Control with Visual Integration
- HomeRobot: Open-Vocabulary Mobile Manipulation
- MimicPlay: Long-Horizon Imitation Learning by Watching Human Play
- UniVLA: Learning to Act Anywhere with Task-centric Latent Actions
- Reflective Planning: Vision-Language Models for Multi-Stage Long-Horizon Robotic Manipulation
- NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation
- LoLA: Long Horizon Latent Action Learning for General Robot Manipulation
- OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning
- Expressive Whole-Body Control for Humanoid Robots
- ExBody2: Advanced Expressive Humanoid Whole-Body Control
- Visual Imitation Enables Contextual Humanoid Control
- LessMimic: Long-Horizon Humanoid Interaction with Unified Distance Field Representations
- Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learning
- Automatic Curricula via Expert Demonstrations
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