Regenerating Soft Robots Through Neural Cellular Automata

Horibe, Kazuya; Walker, Kathryn; Risi, Sebastian

doi:10.1007/978-3-030-72812-0_3

Cited by 26 publications

(31 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Corucci et al (2018) investigated the evolution of walking and swimming soft robots in different environments to explore the effect of major environmental transitions during evolution. Horibe et al (2021) focused on the regeneration of soft robot bodies using growing neural cellular automata when damages are induced to the morphology.…”

Section: Adaptabilitymentioning

confidence: 99%

Criticality-Driven Evolution of Adaptable Morphologies of Voxel-Based Soft-Robots

2021

View full text Add to dashboard Cite

The paradigm of voxel-based soft robots has allowed to shift the complexity from the control algorithm to the robot morphology itself. The bodies of voxel-based soft robots are extremely versatile and more adaptable than the one of traditional robots, since they consist of many simple components that can be freely assembled. Nonetheless, it is still not clear which are the factors responsible for the adaptability of the morphology, which we define as the ability to cope with tasks requiring different skills. In this work, we propose a task-agnostic approach for automatically designing adaptable soft robotic morphologies in simulation, based on the concept of criticality. Criticality is a property belonging to dynamical systems close to a phase transition between the ordered and the chaotic regime. Our hypotheses are that 1) morphologies can be optimized for exhibiting critical dynamics and 2) robots with those morphologies are not worse, on a set of different tasks, than robots with handcrafted morphologies. We introduce a measure of criticality in the context of voxel-based soft robots which is based on the concept of avalanche analysis, often used to assess criticality in biological and artificial neural networks. We let the robot morphologies evolve toward criticality by measuring how close is their avalanche distribution to a power law distribution. We then validate the impact of this approach on the actual adaptability by measuring the resulting robots performance on three different tasks designed to require different skills. The validation results confirm that criticality is indeed a good indicator for the adaptability of a soft robotic morphology, and therefore a promising approach for guiding the design of more adaptive voxel-based soft robots.

show abstract

Section: Adaptabilitymentioning

confidence: 99%

Criticality-Driven Evolution of Adaptable Morphologies of Voxel-Based Soft-Robots

2021

View full text Add to dashboard Cite

show abstract

“…As an extension of this work, it might be possible to explore the effects of pruning on more biologically plausible neural controllers as, e.g., those based on spiking neural networks (SNNs) (Pontes-Filho and Nichele, 2019): we have already highlighted in Section 2.4 that SNNs have been successfully coupled with neuroevolution, thus an extension toward that direction seems a natural continuation of our experimentation. Moreover, the relationship between pruning and forms of regeneration of the controller (Horibe et al, 2021) might be studied. Competing interests.…”

Section: Discussionmentioning

confidence: 99%

Merging pruning and neuroevolution: towards robust and efficient controllers for modular soft robots

Nadizar

Medvet²,

Ramstad³

et al. 2022

The Knowledge Engineering Review

View full text Add to dashboard Cite

Artificial neural networks (ANNs) can be employed as controllers for robotic agents. Their structure is often complex, with many neurons and connections, especially when the robots have many sensors and actuators distributed across their bodies and/or when high expressive power is desirable. Pruning (removing neurons or connections) reduces the complexity of the ANN, thus increasing its energy efficiency, and has been reported to improve the generalization capability, in some cases. In addition, it is well-known that pruning in biological neural networks plays a fundamental role in the development of brains and their ability to learn. In this study, we consider the evolutionary optimization of neural controllers for the case study of Voxel-based soft robots, a kind of modular, bio-inspired soft robots, applying pruning during fitness evaluation. For a locomotion task, and for centralized as well as distributed controllers, we experimentally characterize the effect of different forms of pruning on after-pruning effectiveness, life-long effectiveness, adaptability to new terrains, and behavior. We find that incorporating some forms of pruning in neuroevolution leads to almost equally effective controllers as those evolved without pruning, with the benefit of higher robustness to pruning. We also observe occasional improvements in generalization ability.

show abstract

“…For instance, a locomotion policy trained for a 4-legged ant might not work for a 6-legged one, and an agent that expects to receive 10 inputs won't work if you give it 5, or 20 inputs. 28 The evolutionary computation community started approaching some of these challenges earlier on, by incorporating modularity in the evolutionary process that govern the design of artificial agents. Having agents that are composed of identical but independent modules foster self-organization via local interactions between the modules, enabling systems that are robust to changes in the agent's morphology, an essential requirement in evolutionary systems.…”

Section: Deep Reinforcement Learningmentioning

confidence: 99%

Collective Intelligence for Deep Learning: A Survey of Recent Developments

Ha¹,

Tang²

2021

Preprint

View full text Add to dashboard Cite

In the past decade, we have witnessed the rise of deep learning to dominate the field of artificial intelligence. Advances in artificial neural networks alongside corresponding advances in hardware accelerators with large memory capacity, together with the availability of large datasets enabled researchers and practitioners alike to train and deploy sophisticated neural network models that achieve state-of-the-art performance on tasks across several fields spanning computer vision, natural language processing, and reinforcement learning. However, as these neural networks become bigger, more complex, and more widely used, fundamental problems with current deep learning models become more apparent. State-of-the-art deep learning models are known to suffer from issues that range from poor robustness, inability to adapt to novel task settings, to requiring rigid and inflexible configuration assumptions. Ideas from collective intelligence, in particular concepts from complex systems such as self-organization, emergent behavior, swarm optimization, and cellular systems tend to produce solutions that are robust, adaptable, and have less rigid assumptions about the environment configuration. It is therefore natural to see these ideas incorporated into newer deep learning methods. In this review, we will provide a historical context of neural network research's involvement with complex systems, and highlight several active areas in modern deep learning research that incorporate the principles of collective intelligence to advance its current capabilities. To facilitate a bi-directional flow of ideas, we also discuss work that utilize modern deep learning models to help advance complex systems research. We hope this review can serve as a bridge between complex systems and deep learning communities to facilitate the cross pollination of ideas and foster new collaborations across disciplines.

show abstract

Regenerating Soft Robots Through Neural Cellular Automata

Cited by 26 publications

References 45 publications

Criticality-Driven Evolution of Adaptable Morphologies of Voxel-Based Soft-Robots

Criticality-Driven Evolution of Adaptable Morphologies of Voxel-Based Soft-Robots

Merging pruning and neuroevolution: towards robust and efficient controllers for modular soft robots

Collective Intelligence for Deep Learning: A Survey of Recent Developments

Contact Info

Product

Resources

About