Matches in SemOpenAlex for { <https://semopenalex.org/work/W2949711595> ?p ?o ?g. }
- W2949711595 abstract "Evolutionary robotics is a promising approach to autonomously synthesize machines with abilities that resemble those of animals, but the field suffers from a lack of strong foundations. In particular, evolutionary systems are currently assessed solely by the fitness score their evolved artifacts can achieve for a specific task, whereas such fitness-based comparisons provide limited insights about how the same system would evaluate on different tasks, and its adaptive capabilities to respond to changes in fitness (e.g., from damages to the machine, or in new situations). To counter these limitations, we introduce the concept of signatures, which picture the post-mutation statistical distribution of both behavior diversity (how different are the robot behaviors after a mutation?) and fitness values (how different is the fitness after a mutation?). We tested the relevance of this concept by evolving controllers for hexapod robot locomotion using five different genotype-to-phenotype mappings (direct encoding, generative encoding of open-loop and closed-loop central pattern generators, generative encoding of neural networks, and single-unit pattern generators (SUPG)). We observed a predictive relationship between the evolvability signature of each encoding and the number of generations required by hexapods to adapt from incurred damages. Our study also reveals that, across the five investigated encodings, the SUPG scheme achieved the best evolvability signature, and was always foremost in recovering an effective gait following robot damages. Overall, our evolvability signatures neatly complement existing task-performance benchmarks, and pave the way for stronger foundations for research in evolutionary robotics." @default.
- W2949711595 created "2019-06-27" @default.
- W2949711595 creator A5032227198 @default.
- W2949711595 creator A5046917969 @default.
- W2949711595 date "2014-10-18" @default.
- W2949711595 modified "2023-09-27" @default.
- W2949711595 title "Evolvability signatures of generative encodings: beyond standard performance benchmarks" @default.
- W2949711595 cites W120361141 @default.
- W2949711595 cites W1497734866 @default.
- W2949711595 cites W1539784117 @default.
- W2949711595 cites W1560270123 @default.
- W2949711595 cites W1563281835 @default.
- W2949711595 cites W1565605886 @default.
- W2949711595 cites W1572565176 @default.
- W2949711595 cites W1576818901 @default.
- W2949711595 cites W1595498733 @default.
- W2949711595 cites W1608391772 @default.
- W2949711595 cites W1820629902 @default.
- W2949711595 cites W1830933622 @default.
- W2949711595 cites W1846003205 @default.
- W2949711595 cites W1965675101 @default.
- W2949711595 cites W1970001627 @default.
- W2949711595 cites W1982481553 @default.
- W2949711595 cites W1985125279 @default.
- W2949711595 cites W1987707365 @default.
- W2949711595 cites W1988274707 @default.
- W2949711595 cites W1990157740 @default.
- W2949711595 cites W1990901789 @default.
- W2949711595 cites W1996818689 @default.
- W2949711595 cites W2001685400 @default.
- W2949711595 cites W2003117097 @default.
- W2949711595 cites W2012391952 @default.
- W2949711595 cites W2016264982 @default.
- W2949711595 cites W2017970073 @default.
- W2949711595 cites W2020180319 @default.
- W2949711595 cites W2020399841 @default.
- W2949711595 cites W2020413272 @default.
- W2949711595 cites W2022730625 @default.
- W2949711595 cites W2035679275 @default.
- W2949711595 cites W2036338631 @default.
- W2949711595 cites W2045945255 @default.
- W2949711595 cites W2047919241 @default.
- W2949711595 cites W2048963734 @default.
- W2949711595 cites W2049616526 @default.
- W2949711595 cites W2050494692 @default.
- W2949711595 cites W2052363954 @default.
- W2949711595 cites W2066332274 @default.
- W2949711595 cites W2067211778 @default.
- W2949711595 cites W2072815644 @default.
- W2949711595 cites W2078206945 @default.
- W2949711595 cites W2078364967 @default.
- W2949711595 cites W2080703651 @default.
- W2949711595 cites W2092939357 @default.
- W2949711595 cites W2101822116 @default.
- W2949711595 cites W2101850483 @default.
- W2949711595 cites W2105943646 @default.
- W2949711595 cites W2108020239 @default.
- W2949711595 cites W2111178261 @default.
- W2949711595 cites W2111935653 @default.
- W2949711595 cites W2112413846 @default.
- W2949711595 cites W2116712719 @default.
- W2949711595 cites W2116801943 @default.
- W2949711595 cites W2120652436 @default.
- W2949711595 cites W2122482254 @default.
- W2949711595 cites W2126105956 @default.
- W2949711595 cites W2129578597 @default.
- W2949711595 cites W2130907138 @default.
- W2949711595 cites W2131900713 @default.
- W2949711595 cites W2134735802 @default.
- W2949711595 cites W2138321920 @default.
- W2949711595 cites W2139293933 @default.
- W2949711595 cites W2141791321 @default.
- W2949711595 cites W2143072546 @default.
- W2949711595 cites W2147270524 @default.
- W2949711595 cites W2151083897 @default.
- W2949711595 cites W2155921792 @default.
- W2949711595 cites W2156106639 @default.
- W2949711595 cites W2156174987 @default.
- W2949711595 cites W2156245846 @default.
- W2949711595 cites W2157166695 @default.
- W2949711595 cites W2157246645 @default.
- W2949711595 cites W2161542506 @default.
- W2949711595 cites W2161574998 @default.
- W2949711595 cites W2162274526 @default.
- W2949711595 cites W2163198599 @default.
- W2949711595 cites W2163288162 @default.
- W2949711595 cites W2165379011 @default.
- W2949711595 cites W2166797439 @default.
- W2949711595 cites W2167021024 @default.
- W2949711595 cites W2172259501 @default.
- W2949711595 cites W2315920740 @default.
- W2949711595 cites W2341057945 @default.
- W2949711595 cites W2396471471 @default.
- W2949711595 hasPublicationYear "2014" @default.
- W2949711595 type Work @default.
- W2949711595 sameAs 2949711595 @default.
- W2949711595 citedByCount "1" @default.
- W2949711595 countsByYear W29497115952013 @default.
- W2949711595 crossrefType "posted-content" @default.
- W2949711595 hasAuthorship W2949711595A5032227198 @default.