# RoboLDA: A Probabilistic Generative Model for Uncovering Embodied Hierarchical Structures in Voxel-based Soft Robots

arXiv: https://arxiv.org/abs/2609.29490 · HTML: https://mlsanity.com/paper/2609.29490/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 69 references that are in the map.
- First posted on arXiv 24 Aug 2026.

## Builds on (most cited first, 12 of 12)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [DiffTaichi: Differentiable Programming for Physical Simulation](https://mlsanity.com/paper/1910.00935/) (2019)
- [Autoencoding Variational Inference For Topic Models](https://mlsanity.com/paper/1703.01488/) (2017)
- [MetaMorph: Learning Universal Controllers with Transformers](https://mlsanity.com/paper/2203.11931/) (2022)
- [Neural Graph Evolution: Towards Efficient Automatic Robot Design](https://mlsanity.com/paper/1906.05370/) (2019)
- [Dynamics-Guided Diffusion Model for Sensor-less Robot Manipulator Design](https://mlsanity.com/paper/2402.15038/) (2024)
- [Generating Freeform Endoskeletal Robots](https://mlsanity.com/paper/2412.01036/) (2024)
- [HeteroMorpheus: Universal Control Based on Morphological Heterogeneity Modeling](https://mlsanity.com/paper/2408.01230/) (2024)
- [Natural Selection via Foundation Models for Soft Robot Evolution](https://mlsanity.com/paper/2503.02249/) (2025)
- [Evolutionary Brain-Body Co-Optimization Consistently Fails to Select for Morphological Potential](https://mlsanity.com/paper/2508.17464/) (2025)
- [RoboDesign1M: A Large-scale Dataset for Robot Design Understanding](https://mlsanity.com/paper/2503.06796/) (2025)

## Abstract (arXiv)

Recent advances in robotics highlight hierarchical configurations of robot morphology, where multiple levels of functional substructures synergize to facilitate intelligent behaviors. This hierarchical perspective, while particularly advantageous for voxel-based soft robots (VSRs) to ease design and control complexities, is hindered by its heavy reliance on domain expertise. In this work, we address the following question: can we derive such hierarchical design principles solely from existing successful designs? We answer affirmatively by presenting 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. Through extensive experiments on simulated VSRs, we verify the presence of consistent, intuitive hierarchical patterns underlying high-performing VSR designs and showcase RoboLDA's proficiency to extract and leverage these hierarchical priors for zero-shot robot design in unseen tasks. The generated designs, even without further optimization, achieve on average 106.4% of the optimized performance produced by evolutionary algorithms. Additionally, the organ structures inferred by RoboLDA serve as valid functional substructures, significantly enhancing synergistic motion control when integrated with modular control policies. Our work pioneers hierarchical generative modeling of robot morphology, offering a promising pathway towards more interpretable and generalizable development of embodied agents.