{"work":{"id":"3056ad92-0cea-44e0-bf02-85c07837e2d3","openalex_id":null,"doi":null,"arxiv_id":"2410.03654","raw_key":null,"title":"Learning Humanoid Locomotion over Challenging Terrain","authors":null,"authors_text":"I","year":2024,"venue":"cs.RO","abstract":"Humanoid robots can, in principle, use their legs to go almost anywhere. Developing controllers capable of traversing diverse terrains, however, remains a considerable challenge. Classical controllers are hard to generalize broadly while the learning-based methods have primarily focused on gentle terrains. Here, we present a learning-based approach for blind humanoid locomotion capable of traversing challenging natural and man-made terrain. Our method uses a transformer model to predict the next action based on the history of proprioceptive observations and actions. The model is first pre-trained on a dataset of flat-ground trajectories with sequence modeling, and then fine-tuned on uneven terrain using reinforcement learning. We evaluate our model on a real humanoid robot across a variety of terrains, including rough, deformable, and sloped surfaces. The model demonstrates robust performance, in-context adaptation, and emergent terrain representations. In real-world case studies, our humanoid robot successfully traversed over 4 miles of hiking trails in Berkeley and climbed some of the steepest streets in San Francisco.","external_url":"https://arxiv.org/abs/2410.03654","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-07-10T17:17:25.635982+00:00","pith_arxiv_id":"2410.03654","created_at":"2026-05-15T23:13:16.528866+00:00","updated_at":"2026-07-10T17:17:25.635982+00:00","title_quality_ok":true,"display_title":"Learning humanoid locomotion over challenging terrain","render_title":"Learning humanoid locomotion over challenging terrain"},"hub":{"state":{"tier_text":"hub","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":10,"external_cited_by_count":null},"tier":"hub","role_counts":[],"polarity_counts":[],"runs":{},"summary":{},"graph":{},"authors":[]}}