English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Designing optimal soft modular robots is difficult, due to non-trivialinteractions between morphology and controller. Evolutionary algorithms (EAs),combined with physical simulators, represent a valid tool to overcome thisissue. In this work, we investigate algorithmic solutions to improve theQuality Diversity of co-evolved designs of Tensegrity Soft Modular Robots(TSMRs) for two robotic tasks, namely goal reaching and squeezing trough anarrow passage. To this aim, we use three different EAs, i.e., MAP-Elites andtwo custom algorithms: one based on Viability Evolution (ViE) and NEAT(ViE-NEAT), the other named Double Map MAP-Elites (DM-ME) and devised to seekdiversity while co-evolving robot morphologies and neural network (NN)-basedcontrollers. In detail, DM-ME extends MAP-Elites in that it uses two distinctfeature maps, referring to morphologies and controllers respectively, andintegrates a mechanism to automatically define the NN-related featuredescriptor. Considering the fitness, in the goal-reaching task ViE-NEAToutperforms MAP-Elites and results equivalent to DM-ME. Instead, whenconsidering diversity in terms of "illumination" of the feature space, DM-MEoutperforms the other two algorithms on both tasks, providing a richer pool ofpossible robotic designs, whereas ViE-NEAT shows comparable performance toMAP-Elites on goal reaching, although it does not exploit any map.

Seeking Quality Diversity in Evolutionary Co-design of Morphology and Control of Soft Tensegrity Modular Robots