Trading Control Intelligence for Physical Intelligence: Muscle Drives in Evolved Virtual Creatures
- Dan Lessin,
- Don Fussell,
- Risto Miikkulainen
Publikation:
Konference artikel i Proceeding eller bog/rapport kapitel
Konferencebidrag i proceedings
Peer-reviewOpen Access
Resume
Traditional evolved virtual creatures [12] are actuated using
unevolved, uniform, invisible drives at joints between rigid
segments. In contrast, this paper shows how such conven-
tional actuators can be replaced by evolvable muscle drives
that are a part of the creature’s physical structure. Such a
muscle-drive system replaces control intelligence with mean-
ingful morphological complexity. For instance, the experi-
ments in this paper show that control intelligence sufficient
for locomotion or jumping can be moved almost entirely
from the brain into the musculature of evolved virtual crea-
tures.
This design is important for two reasons: First, the con-
trol intelligence is made visible in the purposeful develop-
ment of muscle density, orientation, attachment points, and
size. Second, the complexity that needs to be evolved for the
brain to control the actuators is reduced, and in some cases
can be essentially eliminated, thus freeing brain power for
higher-level functions. Such designs may thus make it pos-
sible to create more complex behavior than would otherwise
be achievable.
unevolved, uniform, invisible drives at joints between rigid
segments. In contrast, this paper shows how such conven-
tional actuators can be replaced by evolvable muscle drives
that are a part of the creature’s physical structure. Such a
muscle-drive system replaces control intelligence with mean-
ingful morphological complexity. For instance, the experi-
ments in this paper show that control intelligence sufficient
for locomotion or jumping can be moved almost entirely
from the brain into the musculature of evolved virtual crea-
tures.
This design is important for two reasons: First, the con-
trol intelligence is made visible in the purposeful develop-
ment of muscle density, orientation, attachment points, and
size. Second, the complexity that needs to be evolved for the
brain to control the actuators is reduced, and in some cases
can be essentially eliminated, thus freeing brain power for
higher-level functions. Such designs may thus make it pos-
sible to create more complex behavior than would otherwise
be achievable.
Publikation information
Produktionstype
Publikation:
Konference artikel i Proceeding eller bog/rapport kapitel
Konferencebidrag i proceedings
Peer-reviewUndertitel på værtspublikation
GECCO '14Originalsprog
EngelskSider fra-til (Antal sider)
Sider 705-712Publikationsmilepæle
- Udgivet - 12/07/2014
Publikationsstatus
Udgivet - 12/07/2014
Udgivelsessted
New York, NYForlag
Association for Computing Machinery, USAISBN (Trykt)
978-1-4503-2662-9Publication IDs
- Scopus: 84905674549
Titel på værtspublikation
Proceedings of the Genetic and Evolutionary Computation Conference (GECCO) 2014Metrikker
PlumX, åbner i en ny fane
Antal citationer
19
Hentninger
22
