AI is now evolving the physical skeletons of humanoid robots to move more like us.
April 14, 2026
Original Paper
LEGO: Latent-space Exploration for Geometry-aware Optimization of Humanoid Kinematic Design
arXiv · 2604.08636
The Takeaway
The LEGO framework optimizes humanoid joint design by learning a latent space from mechanical parts and human motion data. The robot's physical form is 'grown' to maximize kinematic efficiency rather than being manually engineered.
From the abstract
Designing robot morphologies and kinematics has traditionally relied on human intuition, with little systematic foundation. Motion-design co-optimization offers a promising path toward automation, but two major challenges remain: (i) the vast, unstructured design space and (ii) the difficulty of constructing task-specific loss functions. We propose a new paradigm that minimizes human involvement by (i) learning the design search space from existing mechanical designs, rather than hand-crafting i