Let Humanoids Hike! Integrative Skill Development on Complex Trails
Kwan-Yee Lin, Stella X. Yu
Abstract
Trail's End c) Diverse Motor Skills d) Embodied Navigation Figure 1: We propose training humanoids to hike complex trails, driving integrative skill development across visual perception, decision-making, and motor execution. Center: The humanoid robot (H1) a) equipped with vision, learns to b) anticipate near-future local goals to guide locomotion along the trail with self-autonomy. Bubble size (large → small) indicates anticipated goal direction; color shows temporal order (orange → green → forest). Left: Our LEGO-H framework is universal to different humanoid robots (e.g., G1, a smaller robot) to adaptively c) emerge diverse motor skills, and d) develop embodied path exploration strategies to hike on trails with varied terrains and obstacles.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext a2917891-e303-4918-a3a4-94499885c455Cited by top-tier papers2
- From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement LearningHonglin He, Yukai Ma, Brad Squicciarini, Wayne Wu et al.ICLR 2026 · 19 citations
- IMU-HOI: A Symbiotic Framework for Coherent Human-Object Interaction and Motion Capture via Contact-Conscious Inertial FusionLizhou Lin, Songpengcheng Xia, Zengyuan Lai, Lan Sun et al.CVPR 2026 · 1 citation
Builds on8
- ViViT: A Video Vision TransformerAnurag Arnab, Mostafa Dehghani, Georg Heigold, Chen Sun et al.ICCV 2021 · 2,947 citations
- AMP: adversarial motion priors for stylized physics-based character controlXue Bin Peng, Ze Ma, Pieter Abbeel, Sergey Levine et al.SIGGRAPH 2021 · 392 citations
- ASE: large-scale reusable adversarial skill embeddings for physically simulated charactersXue Bin Peng, Yunrong Guo, Lina Halper, Sergey Levine et al.SIGGRAPH 2022 · 217 citations
- Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal TransformersRuihan Yang, Minghao Zhang, Nicklas Hansen, Huazhe Xu et al.ICLR 2022 · 146 citations
- Universal Humanoid Motion Representations for Physics-Based ControlZhengyi Luo, Jinkun Cao, Josh Merel, Alexander Winkler et al.ICLR 2024 · 125 citations
Related papers
- Towards Adaptive Humanoid Control via Multi-Behavior Distillation and Reinforced Fine-TuningYingnan Zhao, Xinmiao Wang, Dewei Wang, Xinzhe Liu et al.AAAI 2026 · 4 citations
- Hierarchical Skills for Efficient ExplorationJonas Gehring, Gabriel Synnaeve, Andreas Krause, Nicolas UsunierNeurIPS 2021 · 52 citations
- Lifelong Embodied Navigation LearningXudong Wang, Jiahua Dong, Baichen Liu, Qi Lyu et al.ICLR 2026 · 5 citations
- Learning to Coordinate Manipulation Skills via Skill Behavior DiversificationYoungwoon Lee, Jingyun Yang, Joseph J. LimICLR 2020 · 98 citations
- GenH2R: Learning Generalizable Human-to-Robot Handover via Scalable Simulation, Demonstration, and ImitationZifan Wang, Junyu Chen, Ziqing Chen, Pengwei Xie et al.CVPR 2024 · 15 citations
