← Back to Benchmarks
simmediumsim-to-realmetric · varies
AME-2: Agile and Generalized Legged Locomotion via Attention-Based Neural Map Encoding
Description
Achieving agile and generalized legged locomotion across terrains requires tight integration of perception and control, especially under occlusions and sparse footholds. Existing methods have demonstrated agility on parkour courses but often rely on end-to-end sensorimotor models with limited generalization and interpretability. By contrast, methods targeting generalized locomotion typically exhibit limited agility and struggle with visual occlusions. We introduce AME-2, a unified reinforcement