A single neural cellular automaton for body-brain co-evolution

Pontes-Filho, Sidney; Walker, Kathryn; Najarro, Elias; Nichele, Stefano; Risi, Sebastian

doi:10.1145/3520304.3529002

Cited by 5 publications

(7 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The difficulty of co-optimization due to fragile codependence of brain and body is explored [6], and algorithmic solutions that combat the resulting premature convergence through increased diversity are proposed [7]. Different representations and their effects on the evolutionary optimization process are studied in [33,44,54,57,58].…”

Section: Related Workmentioning

confidence: 99%

“…Following the common practice of utilizing neural networks as powerful function approximators [17,22,34,36,37,43,44,[52][53][54], the controllers 𝑓 𝑀 and 𝑓 𝐺 are modeled by a single hidden layer MLP with learnable parameters 𝜃 𝑀 and 𝜃 𝐺 , respectively. The hidden layer consists of 32 units with ReLU activations for both controllers and maps the observations into a feature vector.…”

Section: Controller Modelmentioning

confidence: 99%

“…Following [6,7,24,36,44,54,57,58], we use an evolutionary algorithm to optimize the morphology and control of the soft robots simultaneously. In particular, we use (𝜇 + 𝜆)-Evolution Strategies where 𝜇 = 16 and 𝜆 = 16.…”

Section: Training Algorithmmentioning

confidence: 99%

See 2 more Smart Citations

Modular Controllers Facilitate the Co-Optimization of Morphology and Control in Soft Robots

Mertan

Cheney

2023

Proceedings of the Genetic and Evolutionary Computation Conference

View full text Add to dashboard Cite

Figure 1: Main hypothesis: In the brain-body co-optimization of soft robots, the locomotion performance of modular controllers is significantly more robust than global controllers to perturbations of their robot's morphology. This allows better transfer of that controller to a robot's offspring with morphological mutations. This increases the rate of successful morphological mutations during the co-optimization process and leads to a more efficient and effective search over robot designs.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Controller Modelmentioning

confidence: 99%

See 1 more Smart Citation

Modular Controllers Facilitate the Co-Optimization of Morphology and Control in Soft Robots

Mertan

Cheney

2023

Proceedings of the Genetic and Evolutionary Computation Conference

View full text Add to dashboard Cite

show abstract

“…NCAs exhibit a striking resemblance with the genome-based multi-scale competency architecture of biological life 102 , as illustrated in fig. 1 (C-E): an organism's entire building plan is encoded in its genome (corresponding to the NCA's parameters), while its cells collectively run the self-orchestrated developmental program of morphogenesis (realized by the NCA's layout and ANN architecture) via perception-action cycles at the uni-cellular level (cell state updates in the NCA, c.f., fig.…”

Section: Introductionmentioning

confidence: 99%

“…Employing machine learning methods, such NCAs have been trained to perform selforchestrated pattern-formation (notably, of images from a single "seed" cell) 101 and even the co-evolution of a rigid robot's morphology and its controller has been demonstrated with such NCAs 102 .…”

Section: Introductionmentioning

confidence: 99%

Evolutionary Implications of Multi-Scale Intelligence

Hartl,

Risi,

Levin

2024

Preprint

View full text Add to dashboard Cite

In recent years, the scientific community has increasingly recognized the complex multi-scale competency architecture (MCA) of biology, comprising nested layers of active homeostatic agents, each forming the self orchestrated substrate for the layer above, and, in turn, relying on the structural and functional plasticity of the layer(s) below. The question of how natural selection could give rise to this MCA has been the focus of intense research. Here, we instead investigate the effects of such decision-making competencies of an MCA’s agential components on the process of evolution itself, using in-silico neuroevolution experiments of simulated, minimal developmental biology. We specifically model the process of morphogenesis with neural cellular automata (NCAs) and utilize an evolutionary algorithm to optimize the corresponding model parameters with the objective of collectively self-assembling a two-dimensional spatial target pattern (reliable morphogenesis). Furthermore, we systematically vary the accuracy with which an NCA’s uni-cellular agents can regulate their cell states (simulating stochastic processes and noise during development). This allowed us to continuously scale the agents’ competency levels from a direct encoding scheme (no competency) to an MCA (with perfect reliability in cell decision executions). We demonstrate that an evolutionary process proceeds much more rapidly when evolving the functional parameters of an MCA compared to evolving the target pattern directly. Moreover, the evolved MCAs generalize well toward system parameter changes and even modified objective functions of the evolutionary process. Thus, the adaptive problem-solving competencies of the agential parts in our NCA-based in-silico morphogenesis model strongly affect the evolutionary process, suggesting significant functional implications of the near-ubiquitous competency seen in living matter.

show abstract

Investigating Premature Convergence in Co-optimization of Morphology and Control in Evolved Virtual Soft Robots

Mertan,

Cheney

2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

A single neural cellular automaton for body-brain co-evolution

Cited by 5 publications

References 14 publications

Modular Controllers Facilitate the Co-Optimization of Morphology and Control in Soft Robots

Modular Controllers Facilitate the Co-Optimization of Morphology and Control in Soft Robots

Evolutionary Implications of Multi-Scale Intelligence

Investigating Premature Convergence in Co-optimization of Morphology and Control in Evolved Virtual Soft Robots

Contact Info

Product

Resources

About