Embodied Evolution in Collective Robotics: A Review
arXiv:1709.08992 · doi:10.3389/frobt.2018.00012
Abstract
This paper provides an overview of evolutionary robotics techniques applied to on-line distributed evolution for robot collectives -- namely, embodied evolution. It provides a definition of embodied evolution as well as a thorough description of the underlying concepts and mechanisms. The paper also presents a comprehensive summary of research published in the field since its inception (1999-2017), providing various perspectives to identify the major trends. In particular, we identify a shift from considering embodied evolution as a parallel search method within small robot collectives (fewer than 10 robots) to embodied evolution as an on-line distributed learning method for designing collective behaviours in swarm-like collectives. The paper concludes with a discussion of applications and open questions, providing a milestone for past and an inspiration for future research.
23 pages, 1 figure, 1 table
References in corpus (2)
Cited by in corpus (12)
- Morphological computation and decentralized learning in a swarm of sterically interacting robots
- Artificial Collective Intelligence Engineering: a Survey of Concepts and Perspectives
- Distributed Embodied Evolution over Networks
- DREAM Architecture: a Developmental Approach to Open-Ended Learning in Robotics
- Kinetic theory of decentralized learning for smart active matter
- Meta-brain Models: biologically-inspired cognitive agents
- Continual Learning: Tackling Catastrophic Forgetting in Deep Neural Networks with Replay Processes
- Online adaptation in robots as biological development provides phenotypic plasticity
- What Robot do I Need? Fast Co-Adaptation of Morphology and Control using Graph Neural Networks
- Active Matter as a framework for living systems-inspired Robophysics
- Meta-control of social learning strategies
- On an Immuno-inspired Distributed, Embodied Action-Evolution cum Selection Algorithm