mlsanityData to 14 Oct 2026

Severe Damage Recovery in Evolving Soft Robots through Differentiable Programming

arXiv 2206.06674 ↗First posted 14 Jun 2022cs.NE cs.LG q-bio.PEcited by 4

Not on the map. Why?

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.

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

16 of 59 references.

References · 16

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2014Robots that can adapt like animalscited by 204
  4. 2017Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learningcited by 150
  5. 2018The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communitiescited by 78
  6. 2020Meta-Learning through Hebbian Plasticity in Random Networkscited by 47
  7. 2018Cellular automata as convolutional neural networkscited by 45
  8. 2017Scalable Co-Optimization of Morphology and Control in Embodied Machinescited by 40
  9. 2021Growing 3D Artefacts and Functional Machines with Neural Cellular Automatacited by 38
  10. 2016Reset-free Trial-and-Error Learning for Robot Damage Recoverycited by 24
  11. 2019Deep Neuroevolution of Recurrent and Discrete World Modelscited by 23
  12. 2021Regenerating Soft Robots through Neural Cellular Automatacited by 13
4 more
  1. 2019Automated shapeshifting for function recovery in damaged robotscited by 8
  2. 2020A soft robot that adapts to environments through shape changecited by 5
  3. 2020Reality-assisted evolution of soft robots through large-scale physical experimentation: a reviewcited by 4
  4. 2018Interoceptive robustness through environment-mediated morphological developmentcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025Neural cellular automata: applications to biology and beyond classical AIcited by 9
  2. 2025EngramNCA: a Neural Cellular Automaton Model of Memory Transfercited by 7
  3. 2026BraiNCA: brain-inspired neural cellular automata and applications to morphogenesis and motor controlcited by 1
  4. 2026Applications of Neural Cellular Automata: State of the Art, Challenges and Opportunitiescited by 0