RoboLDA: A Probabilistic Generative Model for Uncovering Embodied Hierarchical Structures in Voxel-based Soft Robots
This work presents RoboLDA, a Bayesian probabilistic model that decomposes VSR morphology generation into a four-level hierarchy:"task-robot-organ-voxel", and is trained via variational inference, which pioneers hierarchical generative modeling of robot morphology.
Jun-Ru Song, Yang Yang, Jing-Dan Shi et al.
· 0 citations