# Evolving Dexterous Robots from Scratch

arXiv: https://arxiv.org/abs/2609.33101 · HTML: https://mlsanity.com/paper/2609.33101/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 35 of its 70 references that are in the map.
- First posted on arXiv 27 Sep 2026.

## Builds on (most cited first, 30 of 35)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [Hierarchical Graph Representation Learning with Differentiable Pooling](https://mlsanity.com/paper/1806.08804/) (2018)
- [Learning Dexterous In-Hand Manipulation](https://mlsanity.com/paper/1808.00177/) (2018)
- [The CMA Evolution Strategy: A Tutorial](https://mlsanity.com/paper/1604.00772/) (2016)
- [DeXtreme: Transfer of Agile In-hand Manipulation from Simulation to Reality](https://mlsanity.com/paper/2210.13702/) (2022)
- [DexGraspNet: A Large-Scale Robotic Dexterous Grasp Dataset for General Objects Based on Simulation](https://mlsanity.com/paper/2210.02697/) (2022)
- [UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-aware Curriculum and Iterative Generalist-Specialist Learning](https://mlsanity.com/paper/2304.00464/) (2023)
- [Neural-Fly Enables Rapid Learning for Agile Flight in Strong Winds](https://mlsanity.com/paper/2205.06908/) (2022)
- [Rotating without Seeing: Towards In-hand Dexterity through Touch](https://mlsanity.com/paper/2303.10880/) (2023)
- [LEAP Hand: Low-Cost, Efficient, and Anthropomorphic Hand for Robot Learning](https://mlsanity.com/paper/2309.06440/) (2023)
- [An End-to-End Differentiable Framework for Contact-Aware Robot Design](https://mlsanity.com/paper/2107.07501/) (2021)
- [Scalable Co-Optimization of Morphology and Control in Embodied Machines](https://mlsanity.com/paper/1706.06133/) (2017)
- [Dexterous Functional Grasping](https://mlsanity.com/paper/2312.02975/) (2023)
- [Learning to Grasp the Ungraspable with Emergent Extrinsic Dexterity](https://mlsanity.com/paper/2211.01500/) (2022)
- [Cross-Embodiment Dexterous Grasping with Reinforcement Learning](https://mlsanity.com/paper/2410.02479/) (2024)
- [Fit2Form: 3D Generative Model for Robot Gripper Form Design](https://mlsanity.com/paper/2011.06498/) (2020)
- [GLSO: Grammar-guided Latent Space Optimization for Sample-efficient Robot Design Automation](https://mlsanity.com/paper/2209.11748/) (2022)
- [Efficient automatic design of robots](https://mlsanity.com/paper/2306.03263/) (2023)
- [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)
- [One Hand to Rule Them All: Canonical Representations for Unified Dexterous Manipulation](https://mlsanity.com/paper/2602.16712/) (2026)
- [Accelerated co-design of robots through morphological pretraining](https://mlsanity.com/paper/2502.10862/) (2025)
- [Evolution and learning in differentiable robots](https://mlsanity.com/paper/2405.14712/) (2024)
- [House of Dextra: Cross-embodied Co-design for Dexterous Hands](https://mlsanity.com/paper/2512.03743/) (2025)
- [SALSA: Semantically-Aware Latent Space Autoencoder](https://mlsanity.com/paper/2310.02744/) (2023)
- [Learning to Design Soft Hands using Reward Models](https://mlsanity.com/paper/2510.17086/) (2025)

## Abstract (arXiv)

Little is known about how to manually design agents capable of dexterous manipulation. Some design principles have been inferred from close examination of how animals manipulate objects, but these structures and behaviors have so far resisted biomimicry and may not be optimal for artificial machines. Here we evolve freeform robots to pick up, hold, rotate, and use diverse objects. Unlike other approaches to optimizing robot hands, we do not presuppose the presence, articulation, or geometry of any part of the body. Although familiar prehensile forms such as tails, beaks, paws and claws may emerge spontaneously under certain conditions--and while such conditions could be of interest to evolutionary biologists--de novo manipulator design can also reveal whole new solutions, overlooked or unknown structures which may be better suited for the task at hand. We use contrastive learning to create a highly searchable genetic embedding of design space, an autoregressive developmental model to decode designs, evolutionary strategies to find good designs, and reinforcement learning to train each evolved design. Winning designs were automatically converted into a manufacturable blueprint, printed, assembled and tested in the real world in a zero-shot manner. The results represent the state-of-the-art in evolutionary robotics in terms of performance, diversity and complexity.