# Severe Damage Recovery in Evolving Soft Robots through Differentiable Programming

arXiv: https://arxiv.org/abs/2206.06674 · HTML: https://mlsanity.com/paper/2206.06674/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 59 references that are in the map.
- First posted on arXiv 14 Jun 2022.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Robots that can adapt like animals](https://mlsanity.com/paper/1407.3501/) (2014)
- [Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning](https://mlsanity.com/paper/1712.06567/) (2017)
- [The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities](https://mlsanity.com/paper/1803.03453/) (2018)
- [Meta-Learning through Hebbian Plasticity in Random Networks](https://mlsanity.com/paper/2007.02686/) (2020)
- [Cellular automata as convolutional neural networks](https://mlsanity.com/paper/1809.02942/) (2018)
- [Scalable Co-Optimization of Morphology and Control in Embodied Machines](https://mlsanity.com/paper/1706.06133/) (2017)
- [Growing 3D Artefacts and Functional Machines with Neural Cellular Automata](https://mlsanity.com/paper/2103.08737/) (2021)
- [Reset-free Trial-and-Error Learning for Robot Damage Recovery](https://mlsanity.com/paper/1610.04213/) (2016)
- [Deep Neuroevolution of Recurrent and Discrete World Models](https://mlsanity.com/paper/1906.08857/) (2019)
- [Regenerating Soft Robots through Neural Cellular Automata](https://mlsanity.com/paper/2102.02579/) (2021)
- [Automated shapeshifting for function recovery in damaged robots](https://mlsanity.com/paper/1905.09264/) (2019)
- [A soft robot that adapts to environments through shape change](https://mlsanity.com/paper/2008.06397/) (2020)
- [Reality-assisted evolution of soft robots through large-scale physical experimentation: a review](https://mlsanity.com/paper/2009.13960/) (2020)
- [Interoceptive robustness through environment-mediated morphological development](https://mlsanity.com/paper/1804.02257/) (2018)

## Built on by (most cited first, 4 of 4)

- [Neural cellular automata: applications to biology and beyond classical AI](https://mlsanity.com/paper/2509.11131/) (2025)
- [EngramNCA: a Neural Cellular Automaton Model of Memory Transfer](https://mlsanity.com/paper/2504.11855/) (2025)
- [BraiNCA: brain-inspired neural cellular automata and applications to morphogenesis and motor control](https://mlsanity.com/paper/2604.01932/) (2026)
- [Applications of Neural Cellular Automata: State of the Art, Challenges and Opportunities](https://mlsanity.com/paper/2609.24595/) (2026)

## Abstract (arXiv)

Biological systems are very robust to morphological damage, but artificial systems (robots) are currently not. In this paper we present a system based on neural cellular automata, in which locomoting robots are evolved and then given the ability to regenerate their morphology from damage through gradient-based training. Our approach thus combines the benefits of evolution to discover a wide range of different robot morphologies, with the efficiency of supervised training for robustness through differentiable update rules. The resulting neural cellular automata are able to grow virtual robots capable of regaining more than 80% of their functionality, even after severe types of morphological damage.