Evolving 3D Morphology and Behavior by Competition

By Karl Sims. 1994

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks (2017, background): “Soon it became evident that intelligence is not only symbol manipulation, but resides also in subsymbolic problem solving abilities emerging from the interaction of brain, body and environment (Steels, 1993; Sims, 1994), so more complex simulators of real-life environment were developed.”
Emergent Tool Use From Multi-Agent Autocurricula (2019, background): “[11] and [20] studied the emergent complexity in morphology and behavior of creatures that coevolved in a simulated 3D world.”
The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities (2018, neutral): “Digital evolution does encompass paradigms like virtual creatures evolving completely in silico [126].”
Evolution of Embodied Intelligence (2003, methodology): “The idea of co-evolving the body and the neural circuit of autonomous robots had already been investigated in simulations by Karl Sims [33], but only recently D. Floreano et al. Fig.”
AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence (2019, background): “Such specialization is especially easy to imagine if the bodies of virtual robots are simultaneously optimized, which is a subﬁeld with a long history [158, 21, 22, 67, 6, 57].”
A scalable pipeline for designing reconfigurable organisms (2020, unknown): “Meanwhile, advances in computational search and 3D printing have yielded scalable methods for designing and training machines in silico (9, 10) and then manufacturing physical instances of them (11–13).”
Neural MMO: A Massively Multiagent Game Environment for Training and Evaluating Intelligent Agents (2019, unknown): “Such projects often consider open-ended skill learning (Yaeger, 1994) and general morphology evolution (Sims, 1994) as primary objectives.”
The Surprising Creativity of Digital Evolution (2018, background): “Why Walk When You Can Somersault? In a seminal work from 1994, Karl Sims evolved 3D virtual creatures that could discover walking, swimming, and jumping behaviors in simulated physical environments (Sims, 1994).”
Central pattern generators for locomotion control in animals and robots: A review (2008, methodology): “Among unsupervised learning techniques, stochastic population-based optimization algorithms such as evolutionary algorithms have extensively been used to design CPG-like models (Lewis, Fagg, & Bekey, 1993; Sims, 1994; Beer & Gallagher, 1992; Gruau & Quatramaran, 1997; Ijspeert & Kodjabachian, 1999; ”
A Hypercube-Based Encoding for Evolving Large-Scale Neural Networks (2009, methodology): “This observation has inspired an active field of research in artificial developmental encodings [2, 4–6, 9, 11, 13–15, 21, 26, 28, 32–34, 36, 37, 39, 46, 52, 57].”
Compositional pattern producing networks: A novel abstraction of development (2007, unknown): “symbol replacement) rules [9, 32, 33, 34, 35, 43, 47, 48, 60, 67, 69 ].”
Abandoning Objectives: Evolution Through the Search for Novelty Alone (2011, background): “There have been several impressive successes (Chellapilla and Fogel, 1999; Hillis, 1991; Sims, 1994), but a common problem is that in practice such arms races may converge to mediocre stable states (Ficici and Pollack, 1998; Pollack et al., 1996; Watson and Pollack, 2001), cycle among various…”
Compositional Pattern Producing Networks : A Novel Abstraction of Development (2007, background): “The apparent connection between development and complexity in biology has inspired significant research into artificial developmental encoding in recent years [4, 6, 10, 11, 12, 13, 22, 24, 25, 26, 27, 32, 33, 34, 35, 38, 41, 42, 43, 44, 47, 48, 54, 55, 57, 60, 67, 69, 80].”
Autonomous Evolution of Topographic Regularities in Artificial Neural Networks (2010, background): “…1990; Koza & Rice, 1991; Lipson & Pollack, 2000; Montana & Davis, 1989; Moriarty & Miikkulainen, 1996; Opitz & Shavlik, 1997; Pujol & Poli, 1998; Sims, 1994; Srinivas & Paranaik, 1991; Stanley & Miikkulainen, 2002b; Yao, 1999; Zhang & Muhlenbein, 1993), the neurons within a HyperNEAT substrate…”