Evolution of Embodied Intelligence

Floreano, Dario; Mondada, Francesco; Pérez-Uribe, Andrés; Roggen, Daniel

doi:10.1007/978-3-540-27833-7_23

Cited by 17 publications

(15 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, if we want to explore morphological issues, and if we want to design entire agents rather than controllers only, we have to devise powerful methods capable of handling these issues. Floreano et al (2004) provide an excellent overview of the field with many illustrations and experiments.…”

Section: Automated Design Methods (Artificial Evolution and Morphogenmentioning

confidence: 99%

“…Moreover, understanding and controlling the highly involved complex dynamics of genetic regulatory networks will require a lot of research (see Bongard, 2003;Eggenberger, 1999;and Banzhaf, 2004, for some preliminary pertinent research). An important aspect will be the understanding of the emergence of hierarchical structures and modularity of the phenotypes (see also Floreano et al, 2004). Second, the physics-based simulation models need to be augmented to allow for more sophisticated agent-environment interactions.…”

Section: Automated Design Methods (Artificial Evolution and Morphogenmentioning

confidence: 99%

See 1 more Smart Citation

Embodied Artificial Intelligence: Trends and Challenges

Pfeifer

Iida

2004

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. The field of Artificial Intelligence, which started roughly half a century ago, has a turbulent history. In the 1980s there has been a major paradigm shift towards embodiment. While embodied artificial intelligence is still highly diverse, changing, and far from "theoretically stable", a certain consensus about the important issues and methods has been achieved or is rapidly emerging. In this non-technical paper we briefly characterize the field, summarize its achievements, and identify important issues for future research. One of the fundamental unresolved problems has been and still is how thinking emerges from an embodied system. Provocatively speaking, the central issue could be captured by the question "How does walking relate to thinking?"

show abstract

Section: Automated Design Methods (Artificial Evolution and Morphogenmentioning

confidence: 99%

Section: Automated Design Methods (Artificial Evolution and Morphogenmentioning

confidence: 99%

Embodied Artificial Intelligence: Trends and Challenges

Pfeifer

Iida

2004

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…They, however, differ because genetic algorithms typically focus on phylogenetic evolution of the learning mechanism over generations of agents (e.g., Floreano, Mondada, Perez-Uribe, & Roggen, 2004), whereas our algorithm focuses on the ontogenetic cognitive development of each agent through the selection of the most useful knowledge. In the future, we nonetheless believe the phylogenetic approach can help us implement mechanisms to adapt our agent's inborn primitive proclivity values based on an evolutionist selection over generations of agents.…”

Section: Comparison With Related Workmentioning

confidence: 99%

An intrinsically-motivated schema mechanism to model and simulate emergent cognition

Georgeon¹,

Ritter²

2012

Cognitive Systems Research

View full text Add to dashboard Cite

We introduce an approach to model and simulate the early mechanisms of emergent cognition based on theories of enactive cognition and on constructivist epistemology. The agent has intrinsic motivations implemented as inborn proclivities that drive the agent in a proactive way. Following these drives, the agent autonomously learns regularities afforded by the environment, and hierarchical sequences of behaviors adapted to these regularities. The agent represents its current situation in terms of perceived affordances that develop through the agent's experience. This situational representation works as an emerging situation awareness that is grounded in the agent's interaction with its environment and that in turn generates expectations and activates adapted behaviors.Through its activity and these aspects of behavior (behavioral proclivity, situation awareness, and hierarchical sequential learning), the agent starts to exhibit emergent sensibility, intrinsic motivation, and autonomous learning. Following theories of cognitive development, we argue that this initial autonomous mechanism provides a basis for implementing autonomously developing cognitive systems.

show abstract

“…Basic sensory and perceptive abilities, which are so easily dismissed as simple because children learn them seemingly with ease, are seen in the embodiment paradigm as complex and essential components of cognition. Situated cognitive principles find their successful implementations in the field of embodied robotics, e.g., subsumption architecture [10], evolutionary strategies [11].…”

Section: Top-down Approachesmentioning

confidence: 99%

Intentional systems: Review of neurodynamics, modeling, and robotics implementation

Kozma

2008

Physics of Life Reviews

View full text Add to dashboard Cite

Evolution of Embodied Intelligence

Cited by 17 publications

References 28 publications

Embodied Artificial Intelligence: Trends and Challenges

Embodied Artificial Intelligence: Trends and Challenges

An intrinsically-motivated schema mechanism to model and simulate emergent cognition

Intentional systems: Review of neurodynamics, modeling, and robotics implementation

Contact Info

Product

Resources

About