UTCS Artificial Intelligence
Trading Control Intelligence for Physical Intelligence: Muscle Drives in Evolved Virtual Creatures (2014)
Author: Dan Lessin, Don Fussell, Risto Miikkulainen
Traditional evolved virtual creatures (Sims, 1994) are actuated using unevolved, uniform, invisible drives at joints between rigid segments. In contrast, this paper shows how such conventional 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 meaningful morphological complexity. For instance, the experiments 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 creatures. This design is important for two reasons: First, the control intelligence is made visible in the purposeful development 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 possible to create more complex behavior than would otherwise be achievable.
dlessin [at] cs utexas edu
Learning Strategic Behavior in Sequential Decision Tasks
2009 - 2014
Evolved Virtual Creatures as Content: Increasing Behavioral and Morphological Complexity
Dan Lessin, PhD Thesis, Computer Science Department, The University of Texas at Austin. Tech Report TR-15-01.
Trading Control Intelligence for Physical Intelligence: Muscle Drives in Evolved Virtual Creatures
Dan Lessin, Don Fussell, Risto Miikkulainen, To Appear In
Proceedings of the Genetic and Evolutionary Computation Conference (GECCO) 2014