Conference PaperLet Humanoids Hike! Integrative Skill Development over Complex TrailsLin, Kwan-Yee; Yu, Stella XHiking on complex trails demands balance, agility, and adaptive decision-making over unpredictable terrain. Current humanoid research remains fragmented and inadequate for hiking: locomotion focuses on motor skills without long-term goals or situational awareness, while semantic navigation overlooks real-world embodiment and local terrain variability. We propose training humanoids to hike on complex trails, driving integrative skill development across visual perception, decision making, and motor execution. We develop a learning framework, LEGO-H, that enables a vision-equipped humanoid robot to hike complex trails autonomously. We introduce two technical innovations: {\bf 1)} A temporal vision transformer variant anticipates future local goals to guide movement, seamlessly integrating locomotion with goal-directed navigation. {\bf 2)} Latent representations of joint movement patterns, combined with hierarchical metric learning, enable smooth policy transfer from privileged training to onboard execution. These components allow LEGO-H to handle diverse physical and environmental challenges without relying on predefined motion patterns. Experiments across varied simulated trails and robot morphologies highlight LEGO-H's versatility and robustness, positioning hiking as a compelling testbed for embodied autonomy and LEGO-H as a baseline for future humanoid development.IEEE/CVF Conference on Computer Vision and Pattern Recognition2025-06-1110677863https://doi.org/2313151; 2215542humanoid locomotion, autonomous navigation, semantic navigation, hikingNational Science Foundation