LEGO: Latent-space Exploration for Geometry-aware Optimization of Humanoid Kinematic Design
This addresses the challenge of systematic robot design automation for robotics researchers, offering a new paradigm that reduces reliance on human intuition.
The paper tackled the problem of automating robot morphology and kinematics design by learning a compact latent space from existing mechanical designs and using human motion data for loss functions, resulting in a principled framework that enables tractable optimization for novel humanoid upper body designs.
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 it, and (ii) defining the loss directly from human motion data via motion retargeting and Procrustes analysis. Using screw-theory-based joint axis representation and isometric manifold learning, we construct a compact, geometry-preserving latent space of humanoid upper body designs in which optimization is tractable. We then solve design optimization in this latent space using gradient-free optimization. Our approach establishes a principled framework for data-driven robot design and demonstrates that leveraging existing designs and human motion can effectively guide the automated discovery of novel robot design.