MAP-Elites Enables Powerful Stepping Stones and Diversity for Modular Robotics

Nordmoen, Jørgen; Veenstra, Frank; Ellefsen, Kai Olav; Glette, Kyrre

doi:10.3389/frobt.2021.639173

Cited by 22 publications

(10 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Algorithms fostering the selection of novel solutions or the generation of population including diversified solutions ( Lehman and Stanley, 2011 ; Mouret and Clune, 2015 ; Nordmoen et al, 2021 ) can also contrast the tendency to remain stuck on phenotypic simple solutions. Consequently, the efficacy of these algorithms can be interpreted at least in part to their ability to overcome the problem discussed above.…”

Section: Discussionmentioning

confidence: 99%

Phenotypic complexity and evolvability in evolving robots

Milano

Nolfi²

2022

Front. Robot. AI

View full text Add to dashboard Cite

The propensity of evolutionary algorithms to generate compact solutions have advantages and disadvantages. On one side, compact solutions can be cheaper, lighter, and faster than less compact ones. On the other hand, compact solutions might lack evolvability, i.e. might have a lower probability to improve as a result of genetic variations. In this work we study the relation between phenotypic complexity and evolvability in the case of soft-robots with varying morphology. We demonstrate a correlation between phenotypic complexity and evolvability. We demonstrate that the tendency to select compact solutions originates from the fact that the fittest robots often correspond to phenotypically simple robots which are robust to genetic variations but lack evolvability. Finally, we demonstrate that the efficacy of the evolutionary process can be improved by increasing the probability of genetic variations which produce a complexification of the agents’ phenotype or by using absolute mutation rates.

show abstract

Section: Discussionmentioning

confidence: 99%

Phenotypic complexity and evolvability in evolving robots

Milano

Nolfi²

2022

Front. Robot. AI

View full text Add to dashboard Cite

show abstract

“…Regarding the controller learning algorithms, there are many recent papers applying learning algorithms to the brains of robots with fixed bodies in order to produce optimal brains ( Schembri et al, 2007 ; Ruud et al, 2017 ; Luck et al, 2019 ; Jelisavcic et al, 2019 ; Lan et al, 2020 ;; Schaff et al, 2019 ; Le Goff et al, 2020 ; van Diggelen et al, 2021 ; Nordmoen et al, 2021 ), naming only a few.…”

Section: Related Workmentioning

confidence: 99%

The Effects of Learning in Morphologically Evolving Robot Systems

et al. 2022

View full text Add to dashboard Cite

Simultaneously evolving morphologies (bodies) and controllers (brains) of robots can cause a mismatch between the inherited body and brain in the offspring. To mitigate this problem, the addition of an infant learning period has been proposed relatively long ago by the so-called Triangle of Life approach. However, an empirical assessment is still lacking to-date. In this paper, we investigate the effects of such a learning mechanism from different perspectives. Using extensive simulations we show that learning can greatly increase task performance and reduce the number of generations required to reach a certain fitness level compared to the purely evolutionary approach. Furthermore, we demonstrate that the evolved morphologies will be also different, even though learning only directly affects the controllers. This provides a quantitative demonstration that changes in the brain can induce changes in the body. Finally, we examine the learning delta defined as the performance difference between the inherited and the learned brain, and find that it is growing throughout the evolutionary process. This shows that evolution produces robots with an increasing plasticity, that is, consecutive generations become better learners and, consequently, they perform better at the given task. Moreover, our results demonstrate that the Triangle of Life is not only a concept of theoretical interest, but a system methodology with practical benefits.

show abstract

“…However, measures of evolvability differ in what features for evolutionary innovation are salient (Pigliucci, 2008). Per one popular definition, "Evolvability is the ability of a biological system to produce phenotypic variation that is both heritable and adaptive" (Payne and Wagner, 2019;Nordmoen et al, 2021). It is important to note two distinct components of this definition: that there is variation (i.e., diversity) being passed from parent to offspring, and that this variation leads to positive effects on fitness.…”

Section: Background and Related Workmentioning

confidence: 99%

On the Entanglement between Evolvability and Fitness: an Experimental Study on Voxel-based Soft Robots

Ferigo¹,

Soros²,

Medvet³

et al. 2022

The 2022 Conference on Artificial Life

View full text Add to dashboard Cite

The concept of evolvability, that is the capacity to produce heritable and adaptive phenotypic variation, is crucial in the current understanding of evolution. However, while its meaning is intuitive, there is no consensus on how to quantitatively measure it. As a consequence, in evolutionary robotics, it is hard to evaluate the interplay between evolvability and fitness and its dependency on key factors like the evolutionary algorithm (EA) or the representation of the individuals. Here, we propose to use MAP-Elites, a well-established Quality Diversity EA, as a support structure for measuring evolvability and for highlighting its interplay with fitness. We map the solutions generated during the evolutionary process to a MAP-Elites-like grid and then visualize their fitness and evolvability as maps. This procedures does not affect the EA execution and can hence be applied to any EA: it only requires to have two descriptors for the solutions that can be used to meaningfully characterize them. We apply this general methodology to the case of Voxel-based Soft Robots (VSR), a kind of modular robots with a body composed of uniform elements whose volume is individually varied by the robot brain. Namely, we optimize the robots for the task of locomotion using evolutionary computation. We consider four representations, i.e., ways of transforming a genotype into a robot, two for the brain only and two for both body and brain of the VSR, and two EAs (MAP-Elites and a simple evolutionary strategy) and examine the evolvability and fitness maps. The experiments suggest that our methodology permits us to discover interesting patterns in the maps: fitness maps appear to depend more on the representation of the solution, whereas evolvability maps appear to depend more on the EA. As an aside, we find that MAP-Elites is particularly effective in the simultaneous evolution of the body and the brain of Voxel-based Soft Robots.

show abstract

MAP-Elites Enables Powerful Stepping Stones and Diversity for Modular Robotics

Cited by 22 publications

References 47 publications

Phenotypic complexity and evolvability in evolving robots

Phenotypic complexity and evolvability in evolving robots

The Effects of Learning in Morphologically Evolving Robot Systems

On the Entanglement between Evolvability and Fitness: an Experimental Study on Voxel-based Soft Robots

Contact Info

Product

Resources

About